blob: b7a8174fd1dc1b50d669606b5256e645f1572356 [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{
Trond Myklebust09c79382006-03-20 13:44:38 -0500368 struct nlm_block *block, *newblock = 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
Trond Myklebust09c79382006-03-20 13:44:38 -0500381 lock->fl.fl_flags &= ~FL_SLEEP;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700382again:
383 /* Lock file against concurrent access */
Neil Brown89e63ef2006-10-04 02:16:06 -0700384 mutex_lock(&file->f_mutex);
Trond Myklebust09c79382006-03-20 13:44:38 -0500385 /* Get existing block (in case client is busy-waiting) */
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) {
388 if (newblock != NULL)
Trond Myklebust92737232006-03-20 13:44:45 -0500389 lock = &newblock->b_call->a_args.lock;
Trond Myklebust09c79382006-03-20 13:44:38 -0500390 } else
Trond Myklebust92737232006-03-20 13:44:45 -0500391 lock = &block->b_call->a_args.lock;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700392
Marc Eshel150b3932007-01-18 16:15:35 -0500393 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Trond Myklebust09c79382006-03-20 13:44:38 -0500394 lock->fl.fl_flags &= ~FL_SLEEP;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700395
Andy Adamsona85f1932006-03-20 13:44:25 -0500396 dprintk("lockd: posix_lock_file returned %d\n", error);
397
Trond Myklebust09c79382006-03-20 13:44:38 -0500398 switch(error) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700399 case 0:
Andy Adamson15dadef2006-03-20 13:44:24 -0500400 ret = nlm_granted;
401 goto out;
Trond Myklebust09c79382006-03-20 13:44:38 -0500402 case -EAGAIN:
403 break;
404 case -EDEADLK:
Andy Adamson15dadef2006-03-20 13:44:24 -0500405 ret = nlm_deadlock;
406 goto out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700407 default: /* includes ENOLCK */
Andy Adamson15dadef2006-03-20 13:44:24 -0500408 ret = nlm_lck_denied_nolocks;
409 goto out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700410 }
411
Trond Myklebust09c79382006-03-20 13:44:38 -0500412 ret = nlm_lck_denied;
413 if (!wait)
414 goto out;
415
416 ret = nlm_lck_blocked;
417 if (block != NULL)
418 goto out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700419
Linus Torvalds1da177e2005-04-16 15:20:36 -0700420 /* If we don't have a block, create and initialize it. Then
421 * retry because we may have slept in kmalloc. */
Neil Brown89e63ef2006-10-04 02:16:06 -0700422 /* We have to release f_mutex as nlmsvc_create_block may try to
Linus Torvalds1da177e2005-04-16 15:20:36 -0700423 * to claim it while doing host garbage collection */
Trond Myklebust09c79382006-03-20 13:44:38 -0500424 if (newblock == NULL) {
Neil Brown89e63ef2006-10-04 02:16:06 -0700425 mutex_unlock(&file->f_mutex);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700426 dprintk("lockd: blocking on this lock (allocating).\n");
Trond Myklebust09c79382006-03-20 13:44:38 -0500427 if (!(newblock = nlmsvc_create_block(rqstp, file, lock, cookie)))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700428 return nlm_lck_denied_nolocks;
429 goto again;
430 }
431
432 /* Append to list of blocked */
Trond Myklebust09c79382006-03-20 13:44:38 -0500433 nlmsvc_insert_block(newblock, NLM_NEVER);
Andy Adamson15dadef2006-03-20 13:44:24 -0500434out:
Neil Brown89e63ef2006-10-04 02:16:06 -0700435 mutex_unlock(&file->f_mutex);
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500436 nlmsvc_release_block(newblock);
437 nlmsvc_release_block(block);
Andy Adamson15dadef2006-03-20 13:44:24 -0500438 dprintk("lockd: nlmsvc_lock returned %u\n", ret);
439 return ret;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700440}
441
442/*
443 * Test for presence of a conflicting lock.
444 */
Al Viro52921e02006-10-19 23:28:46 -0700445__be32
Marc Eshel85f3f1b32006-11-28 16:27:06 -0500446nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
447 struct nlm_lock *lock, struct nlm_lock *conflock,
448 struct nlm_cookie *cookie)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700449{
Marc Eshel5ea0d752006-11-28 16:27:06 -0500450 struct nlm_block *block = NULL;
451 int error;
452 __be32 ret;
453
Linus Torvalds1da177e2005-04-16 15:20:36 -0700454 dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800455 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
456 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700457 lock->fl.fl_type,
458 (long long)lock->fl.fl_start,
459 (long long)lock->fl.fl_end);
460
Marc Eshel5ea0d752006-11-28 16:27:06 -0500461 /* Get existing block (in case client is busy-waiting) */
462 block = nlmsvc_lookup_block(file, lock);
463
464 if (block == NULL) {
465 struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
466
467 if (conf == NULL)
468 return nlm_granted;
469 block = nlmsvc_create_block(rqstp, file, lock, cookie);
470 if (block == NULL) {
471 kfree(conf);
472 return nlm_granted;
473 }
474 block->b_fl = conf;
475 }
476 if (block->b_flags & B_QUEUED) {
477 dprintk("lockd: nlmsvc_testlock deferred block %p flags %d fl %p\n",
478 block, block->b_flags, block->b_fl);
479 if (block->b_flags & B_TIMED_OUT) {
480 nlmsvc_unlink_block(block);
481 return nlm_lck_denied;
482 }
483 if (block->b_flags & B_GOT_CALLBACK) {
484 if (block->b_fl != NULL
485 && block->b_fl->fl_type != F_UNLCK) {
486 lock->fl = *block->b_fl;
487 goto conf_lock;
488 }
489 else {
490 nlmsvc_unlink_block(block);
491 return nlm_granted;
492 }
493 }
494 return nlm_drop_reply;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700495 }
496
Marc Eshel5ea0d752006-11-28 16:27:06 -0500497 error = vfs_test_lock(file->f_file, &lock->fl);
498 if (error == -EINPROGRESS)
499 return nlmsvc_defer_lock_rqst(rqstp, block);
500 if (error) {
501 ret = nlm_lck_denied_nolocks;
502 goto out;
503 }
504 if (lock->fl.fl_type == F_UNLCK) {
505 ret = nlm_granted;
506 goto out;
507 }
508
509conf_lock:
510 dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
511 lock->fl.fl_type, (long long)lock->fl.fl_start,
512 (long long)lock->fl.fl_end);
513 conflock->caller = "somehost"; /* FIXME */
514 conflock->len = strlen(conflock->caller);
515 conflock->oh.len = 0; /* don't return OH info */
516 conflock->svid = lock->fl.fl_pid;
517 conflock->fl.fl_type = lock->fl.fl_type;
518 conflock->fl.fl_start = lock->fl.fl_start;
519 conflock->fl.fl_end = lock->fl.fl_end;
520 ret = nlm_lck_denied;
521out:
522 if (block)
523 nlmsvc_release_block(block);
524 return ret;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700525}
526
527/*
528 * Remove a lock.
529 * This implies a CANCEL call: We send a GRANT_MSG, the client replies
530 * with a GRANT_RES call which gets lost, and calls UNLOCK immediately
531 * afterwards. In this case the block will still be there, and hence
532 * must be removed.
533 */
Al Viro52921e02006-10-19 23:28:46 -0700534__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700535nlmsvc_unlock(struct nlm_file *file, struct nlm_lock *lock)
536{
537 int error;
538
539 dprintk("lockd: nlmsvc_unlock(%s/%ld, pi=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800540 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
541 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700542 lock->fl.fl_pid,
543 (long long)lock->fl.fl_start,
544 (long long)lock->fl.fl_end);
545
546 /* First, cancel any lock that might be there */
547 nlmsvc_cancel_blocked(file, lock);
548
549 lock->fl.fl_type = F_UNLCK;
Marc Eshel150b3932007-01-18 16:15:35 -0500550 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700551
552 return (error < 0)? nlm_lck_denied_nolocks : nlm_granted;
553}
554
555/*
556 * Cancel a previously blocked request.
557 *
558 * A cancel request always overrides any grant that may currently
559 * be in progress.
560 * The calling procedure must check whether the file can be closed.
561 */
Al Viro52921e02006-10-19 23:28:46 -0700562__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700563nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
564{
565 struct nlm_block *block;
J. Bruce Fields64a318e2006-01-03 09:55:46 +0100566 int status = 0;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700567
568 dprintk("lockd: nlmsvc_cancel(%s/%ld, pi=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800569 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
570 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700571 lock->fl.fl_pid,
572 (long long)lock->fl.fl_start,
573 (long long)lock->fl.fl_end);
574
Neil Brown89e63ef2006-10-04 02:16:06 -0700575 mutex_lock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500576 block = nlmsvc_lookup_block(file, lock);
Neil Brown89e63ef2006-10-04 02:16:06 -0700577 mutex_unlock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500578 if (block != NULL) {
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500579 status = nlmsvc_unlink_block(block);
580 nlmsvc_release_block(block);
581 }
J. Bruce Fields64a318e2006-01-03 09:55:46 +0100582 return status ? nlm_lck_denied : nlm_granted;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700583}
584
585/*
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500586 * This is a callback from the filesystem for VFS file lock requests.
587 * It will be used if fl_grant is defined and the filesystem can not
588 * respond to the request immediately.
589 * For GETLK request it will copy the reply to the nlm_block.
590 * For SETLK or SETLKW request it will get the local posix lock.
591 * In all cases it will move the block to the head of nlm_blocked q where
592 * nlmsvc_retry_blocked() can send back a reply for SETLKW or revisit the
593 * deferred rpc for GETLK and SETLK.
594 */
595static void
596nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
597 int result)
598{
599 block->b_flags |= B_GOT_CALLBACK;
600 if (result == 0)
601 block->b_granted = 1;
602 else
603 block->b_flags |= B_TIMED_OUT;
604 if (conf) {
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500605 if (block->b_fl)
606 locks_copy_lock(block->b_fl, conf);
607 }
608}
609
610static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
611 int result)
612{
613 struct nlm_block *block;
614 int rc = -ENOENT;
615
616 lock_kernel();
617 list_for_each_entry(block, &nlm_blocked, b_list) {
618 if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
619 dprintk("lockd: nlmsvc_notify_blocked block %p flags %d\n",
620 block, block->b_flags);
621 if (block->b_flags & B_QUEUED) {
622 if (block->b_flags & B_TIMED_OUT) {
623 rc = -ENOLCK;
624 break;
625 }
626 nlmsvc_update_deferred_block(block, conf, result);
627 } else if (result == 0)
628 block->b_granted = 1;
629
630 nlmsvc_insert_block(block, 0);
631 svc_wake_up(block->b_daemon);
632 rc = 0;
633 break;
634 }
635 }
636 unlock_kernel();
637 if (rc == -ENOENT)
638 printk(KERN_WARNING "lockd: grant for unknown block\n");
639 return rc;
640}
641
642/*
Linus Torvalds1da177e2005-04-16 15:20:36 -0700643 * Unblock a blocked lock request. This is a callback invoked from the
644 * VFS layer when a lock on which we blocked is removed.
645 *
646 * This function doesn't grant the blocked lock instantly, but rather moves
647 * the block to the head of nlm_blocked where it can be picked up by lockd.
648 */
649static void
650nlmsvc_notify_blocked(struct file_lock *fl)
651{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700652 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700653
654 dprintk("lockd: VFS unblock notification for block %p\n", fl);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700655 list_for_each_entry(block, &nlm_blocked, b_list) {
Trond Myklebust92737232006-03-20 13:44:45 -0500656 if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700657 nlmsvc_insert_block(block, 0);
658 svc_wake_up(block->b_daemon);
659 return;
660 }
661 }
662
663 printk(KERN_WARNING "lockd: notification for unknown block!\n");
664}
665
666static int nlmsvc_same_owner(struct file_lock *fl1, struct file_lock *fl2)
667{
668 return fl1->fl_owner == fl2->fl_owner && fl1->fl_pid == fl2->fl_pid;
669}
670
671struct lock_manager_operations nlmsvc_lock_operations = {
672 .fl_compare_owner = nlmsvc_same_owner,
673 .fl_notify = nlmsvc_notify_blocked,
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500674 .fl_grant = nlmsvc_grant_deferred,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700675};
676
677/*
678 * Try to claim a lock that was previously blocked.
679 *
680 * Note that we use both the RPC_GRANTED_MSG call _and_ an async
681 * RPC thread when notifying the client. This seems like overkill...
682 * Here's why:
683 * - we don't want to use a synchronous RPC thread, otherwise
684 * we might find ourselves hanging on a dead portmapper.
685 * - Some lockd implementations (e.g. HP) don't react to
686 * RPC_GRANTED calls; they seem to insist on RPC_GRANTED_MSG calls.
687 */
688static void
689nlmsvc_grant_blocked(struct nlm_block *block)
690{
691 struct nlm_file *file = block->b_file;
Trond Myklebust92737232006-03-20 13:44:45 -0500692 struct nlm_lock *lock = &block->b_call->a_args.lock;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700693 int error;
694
695 dprintk("lockd: grant blocked lock %p\n", block);
696
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500697 kref_get(&block->b_count);
698
Linus Torvalds1da177e2005-04-16 15:20:36 -0700699 /* Unlink block request from list */
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500700 nlmsvc_unlink_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700701
702 /* If b_granted is true this means we've been here before.
703 * Just retry the grant callback, possibly refreshing the RPC
704 * binding */
705 if (block->b_granted) {
706 nlm_rebind_host(block->b_host);
707 goto callback;
708 }
709
710 /* Try the lock operation again */
Trond Myklebust09c79382006-03-20 13:44:38 -0500711 lock->fl.fl_flags |= FL_SLEEP;
Marc Eshel150b3932007-01-18 16:15:35 -0500712 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Trond Myklebust09c79382006-03-20 13:44:38 -0500713 lock->fl.fl_flags &= ~FL_SLEEP;
714
Andy Adamson5de0e502006-03-20 13:44:25 -0500715 switch (error) {
716 case 0:
717 break;
718 case -EAGAIN:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700719 dprintk("lockd: lock still blocked\n");
720 nlmsvc_insert_block(block, NLM_NEVER);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500721 nlmsvc_release_block(block);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500722 return;
Andy Adamson5de0e502006-03-20 13:44:25 -0500723 default:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700724 printk(KERN_WARNING "lockd: unexpected error %d in %s!\n",
725 -error, __FUNCTION__);
726 nlmsvc_insert_block(block, 10 * HZ);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500727 nlmsvc_release_block(block);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500728 return;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700729 }
730
731callback:
732 /* Lock was granted by VFS. */
733 dprintk("lockd: GRANTing blocked lock.\n");
734 block->b_granted = 1;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700735
736 /* Schedule next grant callback in 30 seconds */
737 nlmsvc_insert_block(block, 30 * HZ);
738
739 /* Call the client */
Trond Myklebusta995e9e2007-02-02 15:37:43 -0800740 nlm_async_call(block->b_call, NLMPROC_GRANTED_MSG, &nlmsvc_grant_ops);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700741}
742
743/*
744 * This is the callback from the RPC layer when the NLM_GRANTED_MSG
745 * RPC call has succeeded or timed out.
746 * Like all RPC callbacks, it is invoked by the rpciod process, so it
747 * better not sleep. Therefore, we put the blocked lock on the nlm_blocked
748 * chain once more in order to have it removed by lockd itself (which can
749 * then sleep on the file semaphore without disrupting e.g. the nfs client).
750 */
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100751static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700752{
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100753 struct nlm_rqst *call = data;
Trond Myklebust92737232006-03-20 13:44:45 -0500754 struct nlm_block *block = call->a_block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700755 unsigned long timeout;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700756
757 dprintk("lockd: GRANT_MSG RPC callback\n");
Linus Torvalds1da177e2005-04-16 15:20:36 -0700758
759 /* Technically, we should down the file semaphore here. Since we
760 * move the block towards the head of the queue only, no harm
761 * can be done, though. */
762 if (task->tk_status < 0) {
763 /* RPC error: Re-insert for retransmission */
764 timeout = 10 * HZ;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700765 } else {
766 /* Call was successful, now wait for client callback */
767 timeout = 60 * HZ;
768 }
769 nlmsvc_insert_block(block, timeout);
770 svc_wake_up(block->b_daemon);
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500771}
772
Adrian Bunkec535ce2006-04-18 13:21:50 -0400773static void nlmsvc_grant_release(void *data)
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500774{
Trond Myklebust6041b792006-03-20 13:44:45 -0500775 struct nlm_rqst *call = data;
776
777 nlmsvc_release_block(call->a_block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700778}
779
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100780static const struct rpc_call_ops nlmsvc_grant_ops = {
781 .rpc_call_done = nlmsvc_grant_callback,
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500782 .rpc_release = nlmsvc_grant_release,
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100783};
784
Linus Torvalds1da177e2005-04-16 15:20:36 -0700785/*
786 * We received a GRANT_RES callback. Try to find the corresponding
787 * block.
788 */
789void
Al Viroe8c5c042006-12-13 00:35:03 -0800790nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700791{
792 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700793
Olaf Kirch39be4502006-10-04 02:16:03 -0700794 dprintk("grant_reply: looking for cookie %x, s=%d \n",
795 *(unsigned int *)(cookie->data), status);
796 if (!(block = nlmsvc_find_block(cookie)))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700797 return;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700798
J. Bruce Fieldsf2321422006-01-03 09:55:42 +0100799 if (block) {
Al Viroe8c5c042006-12-13 00:35:03 -0800800 if (status == nlm_lck_denied_grace_period) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700801 /* Try again in a couple of seconds */
802 nlmsvc_insert_block(block, 10 * HZ);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700803 } else {
804 /* Lock is now held by client, or has been rejected.
805 * In both cases, the block should be removed. */
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500806 nlmsvc_unlink_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700807 }
808 }
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500809 nlmsvc_release_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700810}
811
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500812/* Helper function to handle retry of a deferred block.
813 * If it is a blocking lock, call grant_blocked.
814 * For a non-blocking lock or test lock, revisit the request.
815 */
816static void
817retry_deferred_block(struct nlm_block *block)
818{
819 if (!(block->b_flags & B_GOT_CALLBACK))
820 block->b_flags |= B_TIMED_OUT;
821 nlmsvc_insert_block(block, NLM_TIMEOUT);
822 dprintk("revisit block %p flags %d\n", block, block->b_flags);
823 if (block->b_deferred_req) {
824 block->b_deferred_req->revisit(block->b_deferred_req, 0);
825 block->b_deferred_req = NULL;
826 }
827}
828
Linus Torvalds1da177e2005-04-16 15:20:36 -0700829/*
830 * Retry all blocked locks that have been notified. This is where lockd
831 * picks up locks that can be granted, or grant notifications that must
832 * be retransmitted.
833 */
834unsigned long
835nlmsvc_retry_blocked(void)
836{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700837 unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
838 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700839
Olaf Kirch68a2d762006-10-04 02:15:57 -0700840 while (!list_empty(&nlm_blocked)) {
841 block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
842
Linus Torvalds1da177e2005-04-16 15:20:36 -0700843 if (block->b_when == NLM_NEVER)
844 break;
Olaf Kirch68a2d762006-10-04 02:15:57 -0700845 if (time_after(block->b_when,jiffies)) {
846 timeout = block->b_when - jiffies;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700847 break;
Olaf Kirch68a2d762006-10-04 02:15:57 -0700848 }
849
J. Bruce Fieldsf3d43c72006-08-03 15:07:47 -0400850 dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
851 block, block->b_when);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500852 if (block->b_flags & B_QUEUED) {
853 dprintk("nlmsvc_retry_blocked delete block (%p, granted=%d, flags=%d)\n",
854 block, block->b_granted, block->b_flags);
855 retry_deferred_block(block);
856 } else
857 nlmsvc_grant_blocked(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700858 }
859
Olaf Kirch68a2d762006-10-04 02:15:57 -0700860 return timeout;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700861}