xref: /kernel/linux/linux-6.6/fs/ocfs2/dlmfs/dlmfs.c (revision 62306a36) 
1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * dlmfs.c
4 *
5 * Code which implements the kernel side of a minimal userspace
6 * interface to our DLM. This file handles the virtual file system
7 * used for communication with userspace. Credit should go to ramfs,
8 * which was a template for the fs side of this module.
9 *
10 * Copyright (C) 2003, 2004 Oracle.  All rights reserved.
11 */
12
13/* Simple VFS hooks based on: */
14/*
15 * Resizable simple ram filesystem for Linux.
16 *
17 * Copyright (C) 2000 Linus Torvalds.
18 *               2000 Transmeta Corp.
19 */
20
21#include <linux/module.h>
22#include <linux/fs.h>
23#include <linux/pagemap.h>
24#include <linux/types.h>
25#include <linux/slab.h>
26#include <linux/highmem.h>
27#include <linux/init.h>
28#include <linux/string.h>
29#include <linux/backing-dev.h>
30#include <linux/poll.h>
31
32#include <linux/uaccess.h>
33
34#include "../stackglue.h"
35#include "userdlm.h"
36
37#define MLOG_MASK_PREFIX ML_DLMFS
38#include "../cluster/masklog.h"
39
40
41static const struct super_operations dlmfs_ops;
42static const struct file_operations dlmfs_file_operations;
43static const struct inode_operations dlmfs_dir_inode_operations;
44static const struct inode_operations dlmfs_root_inode_operations;
45static const struct inode_operations dlmfs_file_inode_operations;
46static struct kmem_cache *dlmfs_inode_cache;
47
48struct workqueue_struct *user_dlm_worker;
49
50
51
52/*
53 * These are the ABI capabilities of dlmfs.
54 *
55 * Over time, dlmfs has added some features that were not part of the
56 * initial ABI.  Unfortunately, some of these features are not detectable
57 * via standard usage.  For example, Linux's default poll always returns
58 * EPOLLIN, so there is no way for a caller of poll(2) to know when dlmfs
59 * added poll support.  Instead, we provide this list of new capabilities.
60 *
61 * Capabilities is a read-only attribute.  We do it as a module parameter
62 * so we can discover it whether dlmfs is built in, loaded, or even not
63 * loaded.
64 *
65 * The ABI features are local to this machine's dlmfs mount.  This is
66 * distinct from the locking protocol, which is concerned with inter-node
67 * interaction.
68 *
69 * Capabilities:
70 * - bast	: EPOLLIN against the file descriptor of a held lock
71 *		  signifies a bast fired on the lock.
72 */
73#define DLMFS_CAPABILITIES "bast stackglue"
74static int param_set_dlmfs_capabilities(const char *val,
75					const struct kernel_param *kp)
76{
77	printk(KERN_ERR "%s: readonly parameter\n", kp->name);
78	return -EINVAL;
79}
80static int param_get_dlmfs_capabilities(char *buffer,
81					const struct kernel_param *kp)
82{
83	return strlcpy(buffer, DLMFS_CAPABILITIES,
84		       strlen(DLMFS_CAPABILITIES) + 1);
85}
86module_param_call(capabilities, param_set_dlmfs_capabilities,
87		  param_get_dlmfs_capabilities, NULL, 0444);
88MODULE_PARM_DESC(capabilities, DLMFS_CAPABILITIES);
89
90
91/*
92 * decodes a set of open flags into a valid lock level and a set of flags.
93 * returns < 0 if we have invalid flags
94 * flags which mean something to us:
95 * O_RDONLY -> PRMODE level
96 * O_WRONLY -> EXMODE level
97 *
98 * O_NONBLOCK -> NOQUEUE
99 */
100static int dlmfs_decode_open_flags(int open_flags,
101				   int *level,
102				   int *flags)
103{
104	if (open_flags & (O_WRONLY|O_RDWR))
105		*level = DLM_LOCK_EX;
106	else
107		*level = DLM_LOCK_PR;
108
109	*flags = 0;
110	if (open_flags & O_NONBLOCK)
111		*flags |= DLM_LKF_NOQUEUE;
112
113	return 0;
114}
115
116static int dlmfs_file_open(struct inode *inode,
117			   struct file *file)
118{
119	int status, level, flags;
120	struct dlmfs_filp_private *fp = NULL;
121	struct dlmfs_inode_private *ip;
122
123	if (S_ISDIR(inode->i_mode))
124		BUG();
125
126	mlog(0, "open called on inode %lu, flags 0x%x\n", inode->i_ino,
127		file->f_flags);
128
129	status = dlmfs_decode_open_flags(file->f_flags, &level, &flags);
130	if (status < 0)
131		goto bail;
132
133	/* We don't want to honor O_APPEND at read/write time as it
134	 * doesn't make sense for LVB writes. */
135	file->f_flags &= ~O_APPEND;
136
137	fp = kmalloc(sizeof(*fp), GFP_NOFS);
138	if (!fp) {
139		status = -ENOMEM;
140		goto bail;
141	}
142	fp->fp_lock_level = level;
143
144	ip = DLMFS_I(inode);
145
146	status = user_dlm_cluster_lock(&ip->ip_lockres, level, flags);
147	if (status < 0) {
148		/* this is a strange error to return here but I want
149		 * to be able userspace to be able to distinguish a
150		 * valid lock request from one that simply couldn't be
151		 * granted. */
152		if (flags & DLM_LKF_NOQUEUE && status == -EAGAIN)
153			status = -ETXTBSY;
154		kfree(fp);
155		goto bail;
156	}
157
158	file->private_data = fp;
159bail:
160	return status;
161}
162
163static int dlmfs_file_release(struct inode *inode,
164			      struct file *file)
165{
166	int level;
167	struct dlmfs_inode_private *ip = DLMFS_I(inode);
168	struct dlmfs_filp_private *fp = file->private_data;
169
170	if (S_ISDIR(inode->i_mode))
171		BUG();
172
173	mlog(0, "close called on inode %lu\n", inode->i_ino);
174
175	if (fp) {
176		level = fp->fp_lock_level;
177		if (level != DLM_LOCK_IV)
178			user_dlm_cluster_unlock(&ip->ip_lockres, level);
179
180		kfree(fp);
181		file->private_data = NULL;
182	}
183
184	return 0;
185}
186
187/*
188 * We do ->setattr() just to override size changes.  Our size is the size
189 * of the LVB and nothing else.
190 */
191static int dlmfs_file_setattr(struct mnt_idmap *idmap,
192			      struct dentry *dentry, struct iattr *attr)
193{
194	int error;
195	struct inode *inode = d_inode(dentry);
196
197	attr->ia_valid &= ~ATTR_SIZE;
198	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
199	if (error)
200		return error;
201
202	setattr_copy(&nop_mnt_idmap, inode, attr);
203	mark_inode_dirty(inode);
204	return 0;
205}
206
207static __poll_t dlmfs_file_poll(struct file *file, poll_table *wait)
208{
209	__poll_t event = 0;
210	struct inode *inode = file_inode(file);
211	struct dlmfs_inode_private *ip = DLMFS_I(inode);
212
213	poll_wait(file, &ip->ip_lockres.l_event, wait);
214
215	spin_lock(&ip->ip_lockres.l_lock);
216	if (ip->ip_lockres.l_flags & USER_LOCK_BLOCKED)
217		event = EPOLLIN | EPOLLRDNORM;
218	spin_unlock(&ip->ip_lockres.l_lock);
219
220	return event;
221}
222
223static ssize_t dlmfs_file_read(struct file *file,
224			       char __user *buf,
225			       size_t count,
226			       loff_t *ppos)
227{
228	char lvb[DLM_LVB_LEN];
229
230	if (!user_dlm_read_lvb(file_inode(file), lvb))
231		return 0;
232
233	return simple_read_from_buffer(buf, count, ppos, lvb, sizeof(lvb));
234}
235
236static ssize_t dlmfs_file_write(struct file *filp,
237				const char __user *buf,
238				size_t count,
239				loff_t *ppos)
240{
241	char lvb_buf[DLM_LVB_LEN];
242	int bytes_left;
243	struct inode *inode = file_inode(filp);
244
245	mlog(0, "inode %lu, count = %zu, *ppos = %llu\n",
246		inode->i_ino, count, *ppos);
247
248	if (*ppos >= DLM_LVB_LEN)
249		return -ENOSPC;
250
251	/* don't write past the lvb */
252	if (count > DLM_LVB_LEN - *ppos)
253		count = DLM_LVB_LEN - *ppos;
254
255	if (!count)
256		return 0;
257
258	bytes_left = copy_from_user(lvb_buf, buf, count);
259	count -= bytes_left;
260	if (count)
261		user_dlm_write_lvb(inode, lvb_buf, count);
262
263	*ppos = *ppos + count;
264	mlog(0, "wrote %zu bytes\n", count);
265	return count;
266}
267
268static void dlmfs_init_once(void *foo)
269{
270	struct dlmfs_inode_private *ip =
271		(struct dlmfs_inode_private *) foo;
272
273	ip->ip_conn = NULL;
274	ip->ip_parent = NULL;
275
276	inode_init_once(&ip->ip_vfs_inode);
277}
278
279static struct inode *dlmfs_alloc_inode(struct super_block *sb)
280{
281	struct dlmfs_inode_private *ip;
282
283	ip = alloc_inode_sb(sb, dlmfs_inode_cache, GFP_NOFS);
284	if (!ip)
285		return NULL;
286
287	return &ip->ip_vfs_inode;
288}
289
290static void dlmfs_free_inode(struct inode *inode)
291{
292	kmem_cache_free(dlmfs_inode_cache, DLMFS_I(inode));
293}
294
295static void dlmfs_evict_inode(struct inode *inode)
296{
297	int status;
298	struct dlmfs_inode_private *ip;
299	struct user_lock_res *lockres;
300	int teardown;
301
302	clear_inode(inode);
303
304	mlog(0, "inode %lu\n", inode->i_ino);
305
306	ip = DLMFS_I(inode);
307	lockres = &ip->ip_lockres;
308
309	if (S_ISREG(inode->i_mode)) {
310		spin_lock(&lockres->l_lock);
311		teardown = !!(lockres->l_flags & USER_LOCK_IN_TEARDOWN);
312		spin_unlock(&lockres->l_lock);
313		if (!teardown) {
314			status = user_dlm_destroy_lock(lockres);
315			if (status < 0)
316				mlog_errno(status);
317		}
318		iput(ip->ip_parent);
319		goto clear_fields;
320	}
321
322	mlog(0, "we're a directory, ip->ip_conn = 0x%p\n", ip->ip_conn);
323	/* we must be a directory. If required, lets unregister the
324	 * dlm context now. */
325	if (ip->ip_conn)
326		user_dlm_unregister(ip->ip_conn);
327clear_fields:
328	ip->ip_parent = NULL;
329	ip->ip_conn = NULL;
330}
331
332static struct inode *dlmfs_get_root_inode(struct super_block *sb)
333{
334	struct inode *inode = new_inode(sb);
335	umode_t mode = S_IFDIR | 0755;
336
337	if (inode) {
338		inode->i_ino = get_next_ino();
339		inode_init_owner(&nop_mnt_idmap, inode, NULL, mode);
340		inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
341		inc_nlink(inode);
342
343		inode->i_fop = &simple_dir_operations;
344		inode->i_op = &dlmfs_root_inode_operations;
345	}
346
347	return inode;
348}
349
350static struct inode *dlmfs_get_inode(struct inode *parent,
351				     struct dentry *dentry,
352				     umode_t mode)
353{
354	struct super_block *sb = parent->i_sb;
355	struct inode * inode = new_inode(sb);
356	struct dlmfs_inode_private *ip;
357
358	if (!inode)
359		return NULL;
360
361	inode->i_ino = get_next_ino();
362	inode_init_owner(&nop_mnt_idmap, inode, parent, mode);
363	inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
364
365	ip = DLMFS_I(inode);
366	ip->ip_conn = DLMFS_I(parent)->ip_conn;
367
368	switch (mode & S_IFMT) {
369	default:
370		/* for now we don't support anything other than
371		 * directories and regular files. */
372		BUG();
373		break;
374	case S_IFREG:
375		inode->i_op = &dlmfs_file_inode_operations;
376		inode->i_fop = &dlmfs_file_operations;
377
378		i_size_write(inode,  DLM_LVB_LEN);
379
380		user_dlm_lock_res_init(&ip->ip_lockres, dentry);
381
382		/* released at clear_inode time, this insures that we
383		 * get to drop the dlm reference on each lock *before*
384		 * we call the unregister code for releasing parent
385		 * directories. */
386		ip->ip_parent = igrab(parent);
387		BUG_ON(!ip->ip_parent);
388		break;
389	case S_IFDIR:
390		inode->i_op = &dlmfs_dir_inode_operations;
391		inode->i_fop = &simple_dir_operations;
392
393		/* directory inodes start off with i_nlink ==
394		 * 2 (for "." entry) */
395		inc_nlink(inode);
396		break;
397	}
398	return inode;
399}
400
401/*
402 * File creation. Allocate an inode, and we're done..
403 */
404/* SMP-safe */
405static int dlmfs_mkdir(struct mnt_idmap * idmap,
406		       struct inode * dir,
407		       struct dentry * dentry,
408		       umode_t mode)
409{
410	int status;
411	struct inode *inode = NULL;
412	const struct qstr *domain = &dentry->d_name;
413	struct dlmfs_inode_private *ip;
414	struct ocfs2_cluster_connection *conn;
415
416	mlog(0, "mkdir %.*s\n", domain->len, domain->name);
417
418	/* verify that we have a proper domain */
419	if (domain->len >= GROUP_NAME_MAX) {
420		status = -EINVAL;
421		mlog(ML_ERROR, "invalid domain name for directory.\n");
422		goto bail;
423	}
424
425	inode = dlmfs_get_inode(dir, dentry, mode | S_IFDIR);
426	if (!inode) {
427		status = -ENOMEM;
428		mlog_errno(status);
429		goto bail;
430	}
431
432	ip = DLMFS_I(inode);
433
434	conn = user_dlm_register(domain);
435	if (IS_ERR(conn)) {
436		status = PTR_ERR(conn);
437		mlog(ML_ERROR, "Error %d could not register domain \"%.*s\"\n",
438		     status, domain->len, domain->name);
439		goto bail;
440	}
441	ip->ip_conn = conn;
442
443	inc_nlink(dir);
444	d_instantiate(dentry, inode);
445	dget(dentry);	/* Extra count - pin the dentry in core */
446
447	status = 0;
448bail:
449	if (status < 0)
450		iput(inode);
451	return status;
452}
453
454static int dlmfs_create(struct mnt_idmap *idmap,
455			struct inode *dir,
456			struct dentry *dentry,
457			umode_t mode,
458			bool excl)
459{
460	int status = 0;
461	struct inode *inode;
462	const struct qstr *name = &dentry->d_name;
463
464	mlog(0, "create %.*s\n", name->len, name->name);
465
466	/* verify name is valid and doesn't contain any dlm reserved
467	 * characters */
468	if (name->len >= USER_DLM_LOCK_ID_MAX_LEN ||
469	    name->name[0] == '$') {
470		status = -EINVAL;
471		mlog(ML_ERROR, "invalid lock name, %.*s\n", name->len,
472		     name->name);
473		goto bail;
474	}
475
476	inode = dlmfs_get_inode(dir, dentry, mode | S_IFREG);
477	if (!inode) {
478		status = -ENOMEM;
479		mlog_errno(status);
480		goto bail;
481	}
482
483	d_instantiate(dentry, inode);
484	dget(dentry);	/* Extra count - pin the dentry in core */
485bail:
486	return status;
487}
488
489static int dlmfs_unlink(struct inode *dir,
490			struct dentry *dentry)
491{
492	int status;
493	struct inode *inode = d_inode(dentry);
494
495	mlog(0, "unlink inode %lu\n", inode->i_ino);
496
497	/* if there are no current holders, or none that are waiting
498	 * to acquire a lock, this basically destroys our lockres. */
499	status = user_dlm_destroy_lock(&DLMFS_I(inode)->ip_lockres);
500	if (status < 0) {
501		mlog(ML_ERROR, "unlink %pd, error %d from destroy\n",
502		     dentry, status);
503		goto bail;
504	}
505	status = simple_unlink(dir, dentry);
506bail:
507	return status;
508}
509
510static int dlmfs_fill_super(struct super_block * sb,
511			    void * data,
512			    int silent)
513{
514	sb->s_maxbytes = MAX_LFS_FILESIZE;
515	sb->s_blocksize = PAGE_SIZE;
516	sb->s_blocksize_bits = PAGE_SHIFT;
517	sb->s_magic = DLMFS_MAGIC;
518	sb->s_op = &dlmfs_ops;
519	sb->s_root = d_make_root(dlmfs_get_root_inode(sb));
520	if (!sb->s_root)
521		return -ENOMEM;
522	return 0;
523}
524
525static const struct file_operations dlmfs_file_operations = {
526	.open		= dlmfs_file_open,
527	.release	= dlmfs_file_release,
528	.poll		= dlmfs_file_poll,
529	.read		= dlmfs_file_read,
530	.write		= dlmfs_file_write,
531	.llseek		= default_llseek,
532};
533
534static const struct inode_operations dlmfs_dir_inode_operations = {
535	.create		= dlmfs_create,
536	.lookup		= simple_lookup,
537	.unlink		= dlmfs_unlink,
538};
539
540/* this way we can restrict mkdir to only the toplevel of the fs. */
541static const struct inode_operations dlmfs_root_inode_operations = {
542	.lookup		= simple_lookup,
543	.mkdir		= dlmfs_mkdir,
544	.rmdir		= simple_rmdir,
545};
546
547static const struct super_operations dlmfs_ops = {
548	.statfs		= simple_statfs,
549	.alloc_inode	= dlmfs_alloc_inode,
550	.free_inode	= dlmfs_free_inode,
551	.evict_inode	= dlmfs_evict_inode,
552	.drop_inode	= generic_delete_inode,
553};
554
555static const struct inode_operations dlmfs_file_inode_operations = {
556	.getattr	= simple_getattr,
557	.setattr	= dlmfs_file_setattr,
558};
559
560static struct dentry *dlmfs_mount(struct file_system_type *fs_type,
561	int flags, const char *dev_name, void *data)
562{
563	return mount_nodev(fs_type, flags, data, dlmfs_fill_super);
564}
565
566static struct file_system_type dlmfs_fs_type = {
567	.owner		= THIS_MODULE,
568	.name		= "ocfs2_dlmfs",
569	.mount		= dlmfs_mount,
570	.kill_sb	= kill_litter_super,
571};
572MODULE_ALIAS_FS("ocfs2_dlmfs");
573
574static int __init init_dlmfs_fs(void)
575{
576	int status;
577	int cleanup_inode = 0, cleanup_worker = 0;
578
579	dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache",
580				sizeof(struct dlmfs_inode_private),
581				0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
582					SLAB_MEM_SPREAD|SLAB_ACCOUNT),
583				dlmfs_init_once);
584	if (!dlmfs_inode_cache) {
585		status = -ENOMEM;
586		goto bail;
587	}
588	cleanup_inode = 1;
589
590	user_dlm_worker = alloc_workqueue("user_dlm", WQ_MEM_RECLAIM, 0);
591	if (!user_dlm_worker) {
592		status = -ENOMEM;
593		goto bail;
594	}
595	cleanup_worker = 1;
596
597	user_dlm_set_locking_protocol();
598	status = register_filesystem(&dlmfs_fs_type);
599bail:
600	if (status) {
601		if (cleanup_inode)
602			kmem_cache_destroy(dlmfs_inode_cache);
603		if (cleanup_worker)
604			destroy_workqueue(user_dlm_worker);
605	} else
606		printk("OCFS2 User DLM kernel interface loaded\n");
607	return status;
608}
609
610static void __exit exit_dlmfs_fs(void)
611{
612	unregister_filesystem(&dlmfs_fs_type);
613
614	destroy_workqueue(user_dlm_worker);
615
616	/*
617	 * Make sure all delayed rcu free inodes are flushed before we
618	 * destroy cache.
619	 */
620	rcu_barrier();
621	kmem_cache_destroy(dlmfs_inode_cache);
622
623}
624
625MODULE_AUTHOR("Oracle");
626MODULE_LICENSE("GPL");
627MODULE_DESCRIPTION("OCFS2 DLM-Filesystem");
628
629module_init(init_dlmfs_fs)
630module_exit(exit_dlmfs_fs)
631