xref: /kernel/linux/linux-5.10/fs/dlm/user.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright (C) 2006-2010 Red Hat, Inc.  All rights reserved.
4 */
5
6#include <linux/miscdevice.h>
7#include <linux/init.h>
8#include <linux/wait.h>
9#include <linux/file.h>
10#include <linux/fs.h>
11#include <linux/poll.h>
12#include <linux/signal.h>
13#include <linux/spinlock.h>
14#include <linux/dlm.h>
15#include <linux/dlm_device.h>
16#include <linux/slab.h>
17#include <linux/sched/signal.h>
18
19#include "dlm_internal.h"
20#include "lockspace.h"
21#include "lock.h"
22#include "lvb_table.h"
23#include "user.h"
24#include "ast.h"
25#include "config.h"
26
27static const char name_prefix[] = "dlm";
28static const struct file_operations device_fops;
29static atomic_t dlm_monitor_opened;
30static int dlm_monitor_unused = 1;
31
32#ifdef CONFIG_COMPAT
33
34struct dlm_lock_params32 {
35	__u8 mode;
36	__u8 namelen;
37	__u16 unused;
38	__u32 flags;
39	__u32 lkid;
40	__u32 parent;
41	__u64 xid;
42	__u64 timeout;
43	__u32 castparam;
44	__u32 castaddr;
45	__u32 bastparam;
46	__u32 bastaddr;
47	__u32 lksb;
48	char lvb[DLM_USER_LVB_LEN];
49	char name[];
50};
51
52struct dlm_write_request32 {
53	__u32 version[3];
54	__u8 cmd;
55	__u8 is64bit;
56	__u8 unused[2];
57
58	union  {
59		struct dlm_lock_params32 lock;
60		struct dlm_lspace_params lspace;
61		struct dlm_purge_params purge;
62	} i;
63};
64
65struct dlm_lksb32 {
66	__u32 sb_status;
67	__u32 sb_lkid;
68	__u8 sb_flags;
69	__u32 sb_lvbptr;
70};
71
72struct dlm_lock_result32 {
73	__u32 version[3];
74	__u32 length;
75	__u32 user_astaddr;
76	__u32 user_astparam;
77	__u32 user_lksb;
78	struct dlm_lksb32 lksb;
79	__u8 bast_mode;
80	__u8 unused[3];
81	/* Offsets may be zero if no data is present */
82	__u32 lvb_offset;
83};
84
85static void compat_input(struct dlm_write_request *kb,
86			 struct dlm_write_request32 *kb32,
87			 int namelen)
88{
89	kb->version[0] = kb32->version[0];
90	kb->version[1] = kb32->version[1];
91	kb->version[2] = kb32->version[2];
92
93	kb->cmd = kb32->cmd;
94	kb->is64bit = kb32->is64bit;
95	if (kb->cmd == DLM_USER_CREATE_LOCKSPACE ||
96	    kb->cmd == DLM_USER_REMOVE_LOCKSPACE) {
97		kb->i.lspace.flags = kb32->i.lspace.flags;
98		kb->i.lspace.minor = kb32->i.lspace.minor;
99		memcpy(kb->i.lspace.name, kb32->i.lspace.name, namelen);
100	} else if (kb->cmd == DLM_USER_PURGE) {
101		kb->i.purge.nodeid = kb32->i.purge.nodeid;
102		kb->i.purge.pid = kb32->i.purge.pid;
103	} else {
104		kb->i.lock.mode = kb32->i.lock.mode;
105		kb->i.lock.namelen = kb32->i.lock.namelen;
106		kb->i.lock.flags = kb32->i.lock.flags;
107		kb->i.lock.lkid = kb32->i.lock.lkid;
108		kb->i.lock.parent = kb32->i.lock.parent;
109		kb->i.lock.xid = kb32->i.lock.xid;
110		kb->i.lock.timeout = kb32->i.lock.timeout;
111		kb->i.lock.castparam = (void *)(long)kb32->i.lock.castparam;
112		kb->i.lock.castaddr = (void *)(long)kb32->i.lock.castaddr;
113		kb->i.lock.bastparam = (void *)(long)kb32->i.lock.bastparam;
114		kb->i.lock.bastaddr = (void *)(long)kb32->i.lock.bastaddr;
115		kb->i.lock.lksb = (void *)(long)kb32->i.lock.lksb;
116		memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN);
117		memcpy(kb->i.lock.name, kb32->i.lock.name, namelen);
118	}
119}
120
121static void compat_output(struct dlm_lock_result *res,
122			  struct dlm_lock_result32 *res32)
123{
124	memset(res32, 0, sizeof(*res32));
125
126	res32->version[0] = res->version[0];
127	res32->version[1] = res->version[1];
128	res32->version[2] = res->version[2];
129
130	res32->user_astaddr = (__u32)(long)res->user_astaddr;
131	res32->user_astparam = (__u32)(long)res->user_astparam;
132	res32->user_lksb = (__u32)(long)res->user_lksb;
133	res32->bast_mode = res->bast_mode;
134
135	res32->lvb_offset = res->lvb_offset;
136	res32->length = res->length;
137
138	res32->lksb.sb_status = res->lksb.sb_status;
139	res32->lksb.sb_flags = res->lksb.sb_flags;
140	res32->lksb.sb_lkid = res->lksb.sb_lkid;
141	res32->lksb.sb_lvbptr = (__u32)(long)res->lksb.sb_lvbptr;
142}
143#endif
144
145/* Figure out if this lock is at the end of its life and no longer
146   available for the application to use.  The lkb still exists until
147   the final ast is read.  A lock becomes EOL in three situations:
148     1. a noqueue request fails with EAGAIN
149     2. an unlock completes with EUNLOCK
150     3. a cancel of a waiting request completes with ECANCEL/EDEADLK
151   An EOL lock needs to be removed from the process's list of locks.
152   And we can't allow any new operation on an EOL lock.  This is
153   not related to the lifetime of the lkb struct which is managed
154   entirely by refcount. */
155
156static int lkb_is_endoflife(int mode, int status)
157{
158	switch (status) {
159	case -DLM_EUNLOCK:
160		return 1;
161	case -DLM_ECANCEL:
162	case -ETIMEDOUT:
163	case -EDEADLK:
164	case -EAGAIN:
165		if (mode == DLM_LOCK_IV)
166			return 1;
167		break;
168	}
169	return 0;
170}
171
172/* we could possibly check if the cancel of an orphan has resulted in the lkb
173   being removed and then remove that lkb from the orphans list and free it */
174
175void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
176		      int status, uint32_t sbflags, uint64_t seq)
177{
178	struct dlm_ls *ls;
179	struct dlm_user_args *ua;
180	struct dlm_user_proc *proc;
181	int rv;
182
183	if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD))
184		return;
185
186	ls = lkb->lkb_resource->res_ls;
187	mutex_lock(&ls->ls_clear_proc_locks);
188
189	/* If ORPHAN/DEAD flag is set, it means the process is dead so an ast
190	   can't be delivered.  For ORPHAN's, dlm_clear_proc_locks() freed
191	   lkb->ua so we can't try to use it.  This second check is necessary
192	   for cases where a completion ast is received for an operation that
193	   began before clear_proc_locks did its cancel/unlock. */
194
195	if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD))
196		goto out;
197
198	DLM_ASSERT(lkb->lkb_ua, dlm_print_lkb(lkb););
199	ua = lkb->lkb_ua;
200	proc = ua->proc;
201
202	if ((flags & DLM_CB_BAST) && ua->bastaddr == NULL)
203		goto out;
204
205	if ((flags & DLM_CB_CAST) && lkb_is_endoflife(mode, status))
206		lkb->lkb_flags |= DLM_IFL_ENDOFLIFE;
207
208	spin_lock(&proc->asts_spin);
209
210	rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, seq);
211	if (rv < 0) {
212		spin_unlock(&proc->asts_spin);
213		goto out;
214	}
215
216	if (list_empty(&lkb->lkb_cb_list)) {
217		kref_get(&lkb->lkb_ref);
218		list_add_tail(&lkb->lkb_cb_list, &proc->asts);
219		wake_up_interruptible(&proc->wait);
220	}
221	spin_unlock(&proc->asts_spin);
222
223	if (lkb->lkb_flags & DLM_IFL_ENDOFLIFE) {
224		/* N.B. spin_lock locks_spin, not asts_spin */
225		spin_lock(&proc->locks_spin);
226		if (!list_empty(&lkb->lkb_ownqueue)) {
227			list_del_init(&lkb->lkb_ownqueue);
228			dlm_put_lkb(lkb);
229		}
230		spin_unlock(&proc->locks_spin);
231	}
232 out:
233	mutex_unlock(&ls->ls_clear_proc_locks);
234}
235
236static int device_user_lock(struct dlm_user_proc *proc,
237			    struct dlm_lock_params *params)
238{
239	struct dlm_ls *ls;
240	struct dlm_user_args *ua;
241	uint32_t lkid;
242	int error = -ENOMEM;
243
244	ls = dlm_find_lockspace_local(proc->lockspace);
245	if (!ls)
246		return -ENOENT;
247
248	if (!params->castaddr || !params->lksb) {
249		error = -EINVAL;
250		goto out;
251	}
252
253	ua = kzalloc(sizeof(struct dlm_user_args), GFP_NOFS);
254	if (!ua)
255		goto out;
256	ua->proc = proc;
257	ua->user_lksb = params->lksb;
258	ua->castparam = params->castparam;
259	ua->castaddr = params->castaddr;
260	ua->bastparam = params->bastparam;
261	ua->bastaddr = params->bastaddr;
262	ua->xid = params->xid;
263
264	if (params->flags & DLM_LKF_CONVERT) {
265		error = dlm_user_convert(ls, ua,
266				         params->mode, params->flags,
267				         params->lkid, params->lvb,
268					 (unsigned long) params->timeout);
269	} else if (params->flags & DLM_LKF_ORPHAN) {
270		error = dlm_user_adopt_orphan(ls, ua,
271					 params->mode, params->flags,
272					 params->name, params->namelen,
273					 (unsigned long) params->timeout,
274					 &lkid);
275		if (!error)
276			error = lkid;
277	} else {
278		error = dlm_user_request(ls, ua,
279					 params->mode, params->flags,
280					 params->name, params->namelen,
281					 (unsigned long) params->timeout);
282		if (!error)
283			error = ua->lksb.sb_lkid;
284	}
285 out:
286	dlm_put_lockspace(ls);
287	return error;
288}
289
290static int device_user_unlock(struct dlm_user_proc *proc,
291			      struct dlm_lock_params *params)
292{
293	struct dlm_ls *ls;
294	struct dlm_user_args *ua;
295	int error = -ENOMEM;
296
297	ls = dlm_find_lockspace_local(proc->lockspace);
298	if (!ls)
299		return -ENOENT;
300
301	ua = kzalloc(sizeof(struct dlm_user_args), GFP_NOFS);
302	if (!ua)
303		goto out;
304	ua->proc = proc;
305	ua->user_lksb = params->lksb;
306	ua->castparam = params->castparam;
307	ua->castaddr = params->castaddr;
308
309	if (params->flags & DLM_LKF_CANCEL)
310		error = dlm_user_cancel(ls, ua, params->flags, params->lkid);
311	else
312		error = dlm_user_unlock(ls, ua, params->flags, params->lkid,
313					params->lvb);
314 out:
315	dlm_put_lockspace(ls);
316	return error;
317}
318
319static int device_user_deadlock(struct dlm_user_proc *proc,
320				struct dlm_lock_params *params)
321{
322	struct dlm_ls *ls;
323	int error;
324
325	ls = dlm_find_lockspace_local(proc->lockspace);
326	if (!ls)
327		return -ENOENT;
328
329	error = dlm_user_deadlock(ls, params->flags, params->lkid);
330
331	dlm_put_lockspace(ls);
332	return error;
333}
334
335static int dlm_device_register(struct dlm_ls *ls, char *name)
336{
337	int error, len;
338
339	/* The device is already registered.  This happens when the
340	   lockspace is created multiple times from userspace. */
341	if (ls->ls_device.name)
342		return 0;
343
344	error = -ENOMEM;
345	len = strlen(name) + strlen(name_prefix) + 2;
346	ls->ls_device.name = kzalloc(len, GFP_NOFS);
347	if (!ls->ls_device.name)
348		goto fail;
349
350	snprintf((char *)ls->ls_device.name, len, "%s_%s", name_prefix,
351		 name);
352	ls->ls_device.fops = &device_fops;
353	ls->ls_device.minor = MISC_DYNAMIC_MINOR;
354
355	error = misc_register(&ls->ls_device);
356	if (error) {
357		kfree(ls->ls_device.name);
358		/* this has to be set to NULL
359		 * to avoid a double-free in dlm_device_deregister
360		 */
361		ls->ls_device.name = NULL;
362	}
363fail:
364	return error;
365}
366
367int dlm_device_deregister(struct dlm_ls *ls)
368{
369	/* The device is not registered.  This happens when the lockspace
370	   was never used from userspace, or when device_create_lockspace()
371	   calls dlm_release_lockspace() after the register fails. */
372	if (!ls->ls_device.name)
373		return 0;
374
375	misc_deregister(&ls->ls_device);
376	kfree(ls->ls_device.name);
377	return 0;
378}
379
380static int device_user_purge(struct dlm_user_proc *proc,
381			     struct dlm_purge_params *params)
382{
383	struct dlm_ls *ls;
384	int error;
385
386	ls = dlm_find_lockspace_local(proc->lockspace);
387	if (!ls)
388		return -ENOENT;
389
390	error = dlm_user_purge(ls, proc, params->nodeid, params->pid);
391
392	dlm_put_lockspace(ls);
393	return error;
394}
395
396static int device_create_lockspace(struct dlm_lspace_params *params)
397{
398	dlm_lockspace_t *lockspace;
399	struct dlm_ls *ls;
400	int error;
401
402	if (!capable(CAP_SYS_ADMIN))
403		return -EPERM;
404
405	error = dlm_new_lockspace(params->name, dlm_config.ci_cluster_name, params->flags,
406				  DLM_USER_LVB_LEN, NULL, NULL, NULL,
407				  &lockspace);
408	if (error)
409		return error;
410
411	ls = dlm_find_lockspace_local(lockspace);
412	if (!ls)
413		return -ENOENT;
414
415	error = dlm_device_register(ls, params->name);
416	dlm_put_lockspace(ls);
417
418	if (error)
419		dlm_release_lockspace(lockspace, 0);
420	else
421		error = ls->ls_device.minor;
422
423	return error;
424}
425
426static int device_remove_lockspace(struct dlm_lspace_params *params)
427{
428	dlm_lockspace_t *lockspace;
429	struct dlm_ls *ls;
430	int error, force = 0;
431
432	if (!capable(CAP_SYS_ADMIN))
433		return -EPERM;
434
435	ls = dlm_find_lockspace_device(params->minor);
436	if (!ls)
437		return -ENOENT;
438
439	if (params->flags & DLM_USER_LSFLG_FORCEFREE)
440		force = 2;
441
442	lockspace = ls->ls_local_handle;
443	dlm_put_lockspace(ls);
444
445	/* The final dlm_release_lockspace waits for references to go to
446	   zero, so all processes will need to close their device for the
447	   ls before the release will proceed.  release also calls the
448	   device_deregister above.  Converting a positive return value
449	   from release to zero means that userspace won't know when its
450	   release was the final one, but it shouldn't need to know. */
451
452	error = dlm_release_lockspace(lockspace, force);
453	if (error > 0)
454		error = 0;
455	return error;
456}
457
458/* Check the user's version matches ours */
459static int check_version(struct dlm_write_request *req)
460{
461	if (req->version[0] != DLM_DEVICE_VERSION_MAJOR ||
462	    (req->version[0] == DLM_DEVICE_VERSION_MAJOR &&
463	     req->version[1] > DLM_DEVICE_VERSION_MINOR)) {
464
465		printk(KERN_DEBUG "dlm: process %s (%d) version mismatch "
466		       "user (%d.%d.%d) kernel (%d.%d.%d)\n",
467		       current->comm,
468		       task_pid_nr(current),
469		       req->version[0],
470		       req->version[1],
471		       req->version[2],
472		       DLM_DEVICE_VERSION_MAJOR,
473		       DLM_DEVICE_VERSION_MINOR,
474		       DLM_DEVICE_VERSION_PATCH);
475		return -EINVAL;
476	}
477	return 0;
478}
479
480/*
481 * device_write
482 *
483 *   device_user_lock
484 *     dlm_user_request -> request_lock
485 *     dlm_user_convert -> convert_lock
486 *
487 *   device_user_unlock
488 *     dlm_user_unlock -> unlock_lock
489 *     dlm_user_cancel -> cancel_lock
490 *
491 *   device_create_lockspace
492 *     dlm_new_lockspace
493 *
494 *   device_remove_lockspace
495 *     dlm_release_lockspace
496 */
497
498/* a write to a lockspace device is a lock or unlock request, a write
499   to the control device is to create/remove a lockspace */
500
501static ssize_t device_write(struct file *file, const char __user *buf,
502			    size_t count, loff_t *ppos)
503{
504	struct dlm_user_proc *proc = file->private_data;
505	struct dlm_write_request *kbuf;
506	int error;
507
508#ifdef CONFIG_COMPAT
509	if (count < sizeof(struct dlm_write_request32))
510#else
511	if (count < sizeof(struct dlm_write_request))
512#endif
513		return -EINVAL;
514
515	/*
516	 * can't compare against COMPAT/dlm_write_request32 because
517	 * we don't yet know if is64bit is zero
518	 */
519	if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN)
520		return -EINVAL;
521
522	kbuf = memdup_user_nul(buf, count);
523	if (IS_ERR(kbuf))
524		return PTR_ERR(kbuf);
525
526	if (check_version(kbuf)) {
527		error = -EBADE;
528		goto out_free;
529	}
530
531#ifdef CONFIG_COMPAT
532	if (!kbuf->is64bit) {
533		struct dlm_write_request32 *k32buf;
534		int namelen = 0;
535
536		if (count > sizeof(struct dlm_write_request32))
537			namelen = count - sizeof(struct dlm_write_request32);
538
539		k32buf = (struct dlm_write_request32 *)kbuf;
540
541		/* add 1 after namelen so that the name string is terminated */
542		kbuf = kzalloc(sizeof(struct dlm_write_request) + namelen + 1,
543			       GFP_NOFS);
544		if (!kbuf) {
545			kfree(k32buf);
546			return -ENOMEM;
547		}
548
549		if (proc)
550			set_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags);
551
552		compat_input(kbuf, k32buf, namelen);
553		kfree(k32buf);
554	}
555#endif
556
557	/* do we really need this? can a write happen after a close? */
558	if ((kbuf->cmd == DLM_USER_LOCK || kbuf->cmd == DLM_USER_UNLOCK) &&
559	    (proc && test_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags))) {
560		error = -EINVAL;
561		goto out_free;
562	}
563
564	error = -EINVAL;
565
566	switch (kbuf->cmd)
567	{
568	case DLM_USER_LOCK:
569		if (!proc) {
570			log_print("no locking on control device");
571			goto out_free;
572		}
573		error = device_user_lock(proc, &kbuf->i.lock);
574		break;
575
576	case DLM_USER_UNLOCK:
577		if (!proc) {
578			log_print("no locking on control device");
579			goto out_free;
580		}
581		error = device_user_unlock(proc, &kbuf->i.lock);
582		break;
583
584	case DLM_USER_DEADLOCK:
585		if (!proc) {
586			log_print("no locking on control device");
587			goto out_free;
588		}
589		error = device_user_deadlock(proc, &kbuf->i.lock);
590		break;
591
592	case DLM_USER_CREATE_LOCKSPACE:
593		if (proc) {
594			log_print("create/remove only on control device");
595			goto out_free;
596		}
597		error = device_create_lockspace(&kbuf->i.lspace);
598		break;
599
600	case DLM_USER_REMOVE_LOCKSPACE:
601		if (proc) {
602			log_print("create/remove only on control device");
603			goto out_free;
604		}
605		error = device_remove_lockspace(&kbuf->i.lspace);
606		break;
607
608	case DLM_USER_PURGE:
609		if (!proc) {
610			log_print("no locking on control device");
611			goto out_free;
612		}
613		error = device_user_purge(proc, &kbuf->i.purge);
614		break;
615
616	default:
617		log_print("Unknown command passed to DLM device : %d\n",
618			  kbuf->cmd);
619	}
620
621 out_free:
622	kfree(kbuf);
623	return error;
624}
625
626/* Every process that opens the lockspace device has its own "proc" structure
627   hanging off the open file that's used to keep track of locks owned by the
628   process and asts that need to be delivered to the process. */
629
630static int device_open(struct inode *inode, struct file *file)
631{
632	struct dlm_user_proc *proc;
633	struct dlm_ls *ls;
634
635	ls = dlm_find_lockspace_device(iminor(inode));
636	if (!ls)
637		return -ENOENT;
638
639	proc = kzalloc(sizeof(struct dlm_user_proc), GFP_NOFS);
640	if (!proc) {
641		dlm_put_lockspace(ls);
642		return -ENOMEM;
643	}
644
645	proc->lockspace = ls->ls_local_handle;
646	INIT_LIST_HEAD(&proc->asts);
647	INIT_LIST_HEAD(&proc->locks);
648	INIT_LIST_HEAD(&proc->unlocking);
649	spin_lock_init(&proc->asts_spin);
650	spin_lock_init(&proc->locks_spin);
651	init_waitqueue_head(&proc->wait);
652	file->private_data = proc;
653
654	return 0;
655}
656
657static int device_close(struct inode *inode, struct file *file)
658{
659	struct dlm_user_proc *proc = file->private_data;
660	struct dlm_ls *ls;
661
662	ls = dlm_find_lockspace_local(proc->lockspace);
663	if (!ls)
664		return -ENOENT;
665
666	set_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags);
667
668	dlm_clear_proc_locks(ls, proc);
669
670	/* at this point no more lkb's should exist for this lockspace,
671	   so there's no chance of dlm_user_add_ast() being called and
672	   looking for lkb->ua->proc */
673
674	kfree(proc);
675	file->private_data = NULL;
676
677	dlm_put_lockspace(ls);
678	dlm_put_lockspace(ls);  /* for the find in device_open() */
679
680	/* FIXME: AUTOFREE: if this ls is no longer used do
681	   device_remove_lockspace() */
682
683	return 0;
684}
685
686static int copy_result_to_user(struct dlm_user_args *ua, int compat,
687			       uint32_t flags, int mode, int copy_lvb,
688			       char __user *buf, size_t count)
689{
690#ifdef CONFIG_COMPAT
691	struct dlm_lock_result32 result32;
692#endif
693	struct dlm_lock_result result;
694	void *resultptr;
695	int error=0;
696	int len;
697	int struct_len;
698
699	memset(&result, 0, sizeof(struct dlm_lock_result));
700	result.version[0] = DLM_DEVICE_VERSION_MAJOR;
701	result.version[1] = DLM_DEVICE_VERSION_MINOR;
702	result.version[2] = DLM_DEVICE_VERSION_PATCH;
703	memcpy(&result.lksb, &ua->lksb, offsetof(struct dlm_lksb, sb_lvbptr));
704	result.user_lksb = ua->user_lksb;
705
706	/* FIXME: dlm1 provides for the user's bastparam/addr to not be updated
707	   in a conversion unless the conversion is successful.  See code
708	   in dlm_user_convert() for updating ua from ua_tmp.  OpenVMS, though,
709	   notes that a new blocking AST address and parameter are set even if
710	   the conversion fails, so maybe we should just do that. */
711
712	if (flags & DLM_CB_BAST) {
713		result.user_astaddr = ua->bastaddr;
714		result.user_astparam = ua->bastparam;
715		result.bast_mode = mode;
716	} else {
717		result.user_astaddr = ua->castaddr;
718		result.user_astparam = ua->castparam;
719	}
720
721#ifdef CONFIG_COMPAT
722	if (compat)
723		len = sizeof(struct dlm_lock_result32);
724	else
725#endif
726		len = sizeof(struct dlm_lock_result);
727	struct_len = len;
728
729	/* copy lvb to userspace if there is one, it's been updated, and
730	   the user buffer has space for it */
731
732	if (copy_lvb && ua->lksb.sb_lvbptr && count >= len + DLM_USER_LVB_LEN) {
733		if (copy_to_user(buf+len, ua->lksb.sb_lvbptr,
734				 DLM_USER_LVB_LEN)) {
735			error = -EFAULT;
736			goto out;
737		}
738
739		result.lvb_offset = len;
740		len += DLM_USER_LVB_LEN;
741	}
742
743	result.length = len;
744	resultptr = &result;
745#ifdef CONFIG_COMPAT
746	if (compat) {
747		compat_output(&result, &result32);
748		resultptr = &result32;
749	}
750#endif
751
752	if (copy_to_user(buf, resultptr, struct_len))
753		error = -EFAULT;
754	else
755		error = len;
756 out:
757	return error;
758}
759
760static int copy_version_to_user(char __user *buf, size_t count)
761{
762	struct dlm_device_version ver;
763
764	memset(&ver, 0, sizeof(struct dlm_device_version));
765	ver.version[0] = DLM_DEVICE_VERSION_MAJOR;
766	ver.version[1] = DLM_DEVICE_VERSION_MINOR;
767	ver.version[2] = DLM_DEVICE_VERSION_PATCH;
768
769	if (copy_to_user(buf, &ver, sizeof(struct dlm_device_version)))
770		return -EFAULT;
771	return sizeof(struct dlm_device_version);
772}
773
774/* a read returns a single ast described in a struct dlm_lock_result */
775
776static ssize_t device_read(struct file *file, char __user *buf, size_t count,
777			   loff_t *ppos)
778{
779	struct dlm_user_proc *proc = file->private_data;
780	struct dlm_lkb *lkb;
781	DECLARE_WAITQUEUE(wait, current);
782	struct dlm_callback cb;
783	int rv, resid, copy_lvb = 0;
784	int old_mode, new_mode;
785
786	if (count == sizeof(struct dlm_device_version)) {
787		rv = copy_version_to_user(buf, count);
788		return rv;
789	}
790
791	if (!proc) {
792		log_print("non-version read from control device %zu", count);
793		return -EINVAL;
794	}
795
796#ifdef CONFIG_COMPAT
797	if (count < sizeof(struct dlm_lock_result32))
798#else
799	if (count < sizeof(struct dlm_lock_result))
800#endif
801		return -EINVAL;
802
803 try_another:
804
805	/* do we really need this? can a read happen after a close? */
806	if (test_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags))
807		return -EINVAL;
808
809	spin_lock(&proc->asts_spin);
810	if (list_empty(&proc->asts)) {
811		if (file->f_flags & O_NONBLOCK) {
812			spin_unlock(&proc->asts_spin);
813			return -EAGAIN;
814		}
815
816		add_wait_queue(&proc->wait, &wait);
817
818	repeat:
819		set_current_state(TASK_INTERRUPTIBLE);
820		if (list_empty(&proc->asts) && !signal_pending(current)) {
821			spin_unlock(&proc->asts_spin);
822			schedule();
823			spin_lock(&proc->asts_spin);
824			goto repeat;
825		}
826		set_current_state(TASK_RUNNING);
827		remove_wait_queue(&proc->wait, &wait);
828
829		if (signal_pending(current)) {
830			spin_unlock(&proc->asts_spin);
831			return -ERESTARTSYS;
832		}
833	}
834
835	/* if we empty lkb_callbacks, we don't want to unlock the spinlock
836	   without removing lkb_cb_list; so empty lkb_cb_list is always
837	   consistent with empty lkb_callbacks */
838
839	lkb = list_entry(proc->asts.next, struct dlm_lkb, lkb_cb_list);
840
841	/* rem_lkb_callback sets a new lkb_last_cast */
842	old_mode = lkb->lkb_last_cast.mode;
843
844	rv = dlm_rem_lkb_callback(lkb->lkb_resource->res_ls, lkb, &cb, &resid);
845	if (rv < 0) {
846		/* this shouldn't happen; lkb should have been removed from
847		   list when resid was zero */
848		log_print("dlm_rem_lkb_callback empty %x", lkb->lkb_id);
849		list_del_init(&lkb->lkb_cb_list);
850		spin_unlock(&proc->asts_spin);
851		/* removes ref for proc->asts, may cause lkb to be freed */
852		dlm_put_lkb(lkb);
853		goto try_another;
854	}
855	if (!resid)
856		list_del_init(&lkb->lkb_cb_list);
857	spin_unlock(&proc->asts_spin);
858
859	if (cb.flags & DLM_CB_SKIP) {
860		/* removes ref for proc->asts, may cause lkb to be freed */
861		if (!resid)
862			dlm_put_lkb(lkb);
863		goto try_another;
864	}
865
866	if (cb.flags & DLM_CB_CAST) {
867		new_mode = cb.mode;
868
869		if (!cb.sb_status && lkb->lkb_lksb->sb_lvbptr &&
870		    dlm_lvb_operations[old_mode + 1][new_mode + 1])
871			copy_lvb = 1;
872
873		lkb->lkb_lksb->sb_status = cb.sb_status;
874		lkb->lkb_lksb->sb_flags = cb.sb_flags;
875	}
876
877	rv = copy_result_to_user(lkb->lkb_ua,
878				 test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags),
879				 cb.flags, cb.mode, copy_lvb, buf, count);
880
881	/* removes ref for proc->asts, may cause lkb to be freed */
882	if (!resid)
883		dlm_put_lkb(lkb);
884
885	return rv;
886}
887
888static __poll_t device_poll(struct file *file, poll_table *wait)
889{
890	struct dlm_user_proc *proc = file->private_data;
891
892	poll_wait(file, &proc->wait, wait);
893
894	spin_lock(&proc->asts_spin);
895	if (!list_empty(&proc->asts)) {
896		spin_unlock(&proc->asts_spin);
897		return EPOLLIN | EPOLLRDNORM;
898	}
899	spin_unlock(&proc->asts_spin);
900	return 0;
901}
902
903int dlm_user_daemon_available(void)
904{
905	/* dlm_controld hasn't started (or, has started, but not
906	   properly populated configfs) */
907
908	if (!dlm_our_nodeid())
909		return 0;
910
911	/* This is to deal with versions of dlm_controld that don't
912	   know about the monitor device.  We assume that if the
913	   dlm_controld was started (above), but the monitor device
914	   was never opened, that it's an old version.  dlm_controld
915	   should open the monitor device before populating configfs. */
916
917	if (dlm_monitor_unused)
918		return 1;
919
920	return atomic_read(&dlm_monitor_opened) ? 1 : 0;
921}
922
923static int ctl_device_open(struct inode *inode, struct file *file)
924{
925	file->private_data = NULL;
926	return 0;
927}
928
929static int ctl_device_close(struct inode *inode, struct file *file)
930{
931	return 0;
932}
933
934static int monitor_device_open(struct inode *inode, struct file *file)
935{
936	atomic_inc(&dlm_monitor_opened);
937	dlm_monitor_unused = 0;
938	return 0;
939}
940
941static int monitor_device_close(struct inode *inode, struct file *file)
942{
943	if (atomic_dec_and_test(&dlm_monitor_opened))
944		dlm_stop_lockspaces();
945	return 0;
946}
947
948static const struct file_operations device_fops = {
949	.open    = device_open,
950	.release = device_close,
951	.read    = device_read,
952	.write   = device_write,
953	.poll    = device_poll,
954	.owner   = THIS_MODULE,
955	.llseek  = noop_llseek,
956};
957
958static const struct file_operations ctl_device_fops = {
959	.open    = ctl_device_open,
960	.release = ctl_device_close,
961	.read    = device_read,
962	.write   = device_write,
963	.owner   = THIS_MODULE,
964	.llseek  = noop_llseek,
965};
966
967static struct miscdevice ctl_device = {
968	.name  = "dlm-control",
969	.fops  = &ctl_device_fops,
970	.minor = MISC_DYNAMIC_MINOR,
971};
972
973static const struct file_operations monitor_device_fops = {
974	.open    = monitor_device_open,
975	.release = monitor_device_close,
976	.owner   = THIS_MODULE,
977	.llseek  = noop_llseek,
978};
979
980static struct miscdevice monitor_device = {
981	.name  = "dlm-monitor",
982	.fops  = &monitor_device_fops,
983	.minor = MISC_DYNAMIC_MINOR,
984};
985
986int __init dlm_user_init(void)
987{
988	int error;
989
990	atomic_set(&dlm_monitor_opened, 0);
991
992	error = misc_register(&ctl_device);
993	if (error) {
994		log_print("misc_register failed for control device");
995		goto out;
996	}
997
998	error = misc_register(&monitor_device);
999	if (error) {
1000		log_print("misc_register failed for monitor device");
1001		misc_deregister(&ctl_device);
1002	}
1003 out:
1004	return error;
1005}
1006
1007void dlm_user_exit(void)
1008{
1009	misc_deregister(&ctl_device);
1010	misc_deregister(&monitor_device);
1011}
1012
1013