summaryrefslogtreecommitdiff
path: root/fs/orangefs/inode.c
blob: 0166faabf8f2980f0c4e1cecfbdbd439a5c54c15 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
/*
 * (C) 2001 Clemson University and The University of Chicago
 *
 * See COPYING in top-level directory.
 */

/*
 *  Linux VFS inode operations.
 */

#include "protocol.h"
#include "orangefs-kernel.h"
#include "orangefs-bufmap.h"

static int read_one_page(struct page *page)
{
	int ret;
	int max_block;
	ssize_t bytes_read = 0;
	struct inode *inode = page->mapping->host;
	const __u32 blocksize = PAGE_SIZE;	/* inode->i_blksize */
	const __u32 blockbits = PAGE_SHIFT;	/* inode->i_blkbits */
	struct iov_iter to;
	struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE};

	iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE);

	gossip_debug(GOSSIP_INODE_DEBUG,
		    "orangefs_readpage called with page %p\n",
		     page);

	max_block = ((inode->i_size / blocksize) + 1);

	if (page->index < max_block) {
		loff_t blockptr_offset = (((loff_t) page->index) << blockbits);

		bytes_read = orangefs_inode_read(inode,
						 &to,
						 &blockptr_offset,
						 inode->i_size);
	}
	/* this will only zero remaining unread portions of the page data */
	iov_iter_zero(~0U, &to);
	/* takes care of potential aliasing */
	flush_dcache_page(page);
	if (bytes_read < 0) {
		ret = bytes_read;
		SetPageError(page);
	} else {
		SetPageUptodate(page);
		if (PageError(page))
			ClearPageError(page);
		ret = 0;
	}
	/* unlock the page after the ->readpage() routine completes */
	unlock_page(page);
	return ret;
}

static int orangefs_readpage(struct file *file, struct page *page)
{
	return read_one_page(page);
}

static int orangefs_readpages(struct file *file,
			   struct address_space *mapping,
			   struct list_head *pages,
			   unsigned nr_pages)
{
	int page_idx;
	int ret;

	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpages called\n");

	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
		struct page *page;

		page = list_entry(pages->prev, struct page, lru);
		list_del(&page->lru);
		if (!add_to_page_cache(page,
				       mapping,
				       page->index,
				       GFP_KERNEL)) {
			ret = read_one_page(page);
			gossip_debug(GOSSIP_INODE_DEBUG,
				"failure adding page to cache, read_one_page returned: %d\n",
				ret);
	      } else {
			put_page(page);
	      }
	}
	BUG_ON(!list_empty(pages));
	return 0;
}

static void orangefs_invalidatepage(struct page *page,
				 unsigned int offset,
				 unsigned int length)
{
	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_invalidatepage called on page %p "
		     "(offset is %u)\n",
		     page,
		     offset);

	ClearPageUptodate(page);
	ClearPageMappedToDisk(page);
	return;

}

static int orangefs_releasepage(struct page *page, gfp_t foo)
{
	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_releasepage called on page %p\n",
		     page);
	return 0;
}

/*
 * Having a direct_IO entry point in the address_space_operations
 * struct causes the kernel to allows us to use O_DIRECT on
 * open. Nothing will ever call this thing, but in the future we
 * will need to be able to use O_DIRECT on open in order to support
 * AIO. Modeled after NFS, they do this too.
 */
/*
 * static ssize_t orangefs_direct_IO(int rw,
 *			struct kiocb *iocb,
 *			struct iov_iter *iter,
 *			loff_t offset)
 *{
 *	gossip_debug(GOSSIP_INODE_DEBUG,
 *		     "orangefs_direct_IO: %s\n",
 *		     iocb->ki_filp->f_path.dentry->d_name.name);
 *
 *	return -EINVAL;
 *}
 */

struct backing_dev_info orangefs_backing_dev_info = {
	.name = "orangefs",
	.ra_pages = 0,
	.capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
};

/** ORANGEFS2 implementation of address space operations */
const struct address_space_operations orangefs_address_operations = {
	.readpage = orangefs_readpage,
	.readpages = orangefs_readpages,
	.invalidatepage = orangefs_invalidatepage,
	.releasepage = orangefs_releasepage,
/*	.direct_IO = orangefs_direct_IO */
};

static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr)
{
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
	struct orangefs_kernel_op_s *new_op;
	loff_t orig_size;
	int ret = -EINVAL;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "%s: %pU: Handle is %pU | fs_id %d | size is %llu\n",
		     __func__,
		     get_khandle_from_ino(inode),
		     &orangefs_inode->refn.khandle,
		     orangefs_inode->refn.fs_id,
		     iattr->ia_size);

	/* Ensure that we have a up to date size, so we know if it changed. */
	ret = orangefs_inode_getattr(inode, 0, 1);
	if (ret == -ESTALE)
		ret = -EIO;
	if (ret) {
		gossip_err("%s: orangefs_inode_getattr failed, ret:%d:.\n",
		    __func__, ret);
		return ret;
	}
	orig_size = i_size_read(inode);

	truncate_setsize(inode, iattr->ia_size);

	new_op = op_alloc(ORANGEFS_VFS_OP_TRUNCATE);
	if (!new_op)
		return -ENOMEM;

	new_op->upcall.req.truncate.refn = orangefs_inode->refn;
	new_op->upcall.req.truncate.size = (__s64) iattr->ia_size;

	ret = service_operation(new_op, __func__,
				get_interruptible_flag(inode));

	/*
	 * the truncate has no downcall members to retrieve, but
	 * the status value tells us if it went through ok or not
	 */
	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs: orangefs_truncate got return value of %d\n",
		     ret);

	op_release(new_op);

	if (ret != 0)
		return ret;

	/*
	 * Only change the c/mtime if we are changing the size or we are
	 * explicitly asked to change it.  This handles the semantic difference
	 * between truncate() and ftruncate() as implemented in the VFS.
	 *
	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
	 * special case where we need to update the times despite not having
	 * these flags set.  For all other operations the VFS set these flags
	 * explicitly if it wants a timestamp update.
	 */
	if (orig_size != i_size_read(inode) &&
	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
		iattr->ia_ctime = iattr->ia_mtime =
			current_fs_time(inode->i_sb);
		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
	}

	return ret;
}

/*
 * Change attributes of an object referenced by dentry.
 */
int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
{
	int ret = -EINVAL;
	struct inode *inode = dentry->d_inode;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_setattr: called on %s\n",
		     dentry->d_name.name);

	ret = inode_change_ok(inode, iattr);
	if (ret)
		goto out;

	if ((iattr->ia_valid & ATTR_SIZE) &&
	    iattr->ia_size != i_size_read(inode)) {
		ret = orangefs_setattr_size(inode, iattr);
		if (ret)
			goto out;
	}

	setattr_copy(inode, iattr);
	mark_inode_dirty(inode);

	ret = orangefs_inode_setattr(inode, iattr);
	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_setattr: inode_setattr returned %d\n",
		     ret);

	if (!ret && (iattr->ia_valid & ATTR_MODE))
		/* change mod on a file that has ACLs */
		ret = posix_acl_chmod(inode, inode->i_mode);

out:
	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_setattr: returning %d\n", ret);
	return ret;
}

/*
 * Obtain attributes of an object given a dentry
 */
int orangefs_getattr(struct vfsmount *mnt,
		  struct dentry *dentry,
		  struct kstat *kstat)
{
	int ret = -ENOENT;
	struct inode *inode = dentry->d_inode;
	struct orangefs_inode_s *orangefs_inode = NULL;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_getattr: called on %s\n",
		     dentry->d_name.name);

	ret = orangefs_inode_getattr(inode, 0, 1);
	if (ret == 0) {
		generic_fillattr(inode, kstat);

		/* override block size reported to stat */
		orangefs_inode = ORANGEFS_I(inode);
		kstat->blksize = orangefs_inode->blksize;
	}
	return ret;
}

int orangefs_permission(struct inode *inode, int mask)
{
	int ret;

	if (mask & MAY_NOT_BLOCK)
		return -ECHILD;

	gossip_debug(GOSSIP_INODE_DEBUG, "%s: refreshing\n", __func__);

	/* Make sure the permission (and other common attrs) are up to date. */
	ret = orangefs_inode_getattr(inode, 0, 0);
	if (ret < 0)
		return ret;

	return generic_permission(inode, mask);
}

/* ORANGEDS2 implementation of VFS inode operations for files */
struct inode_operations orangefs_file_inode_operations = {
	.get_acl = orangefs_get_acl,
	.set_acl = orangefs_set_acl,
	.setattr = orangefs_setattr,
	.getattr = orangefs_getattr,
	.setxattr = generic_setxattr,
	.getxattr = generic_getxattr,
	.listxattr = orangefs_listxattr,
	.removexattr = generic_removexattr,
	.permission = orangefs_permission,
};

static int orangefs_init_iops(struct inode *inode)
{
	inode->i_mapping->a_ops = &orangefs_address_operations;

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		inode->i_op = &orangefs_file_inode_operations;
		inode->i_fop = &orangefs_file_operations;
		inode->i_blkbits = PAGE_SHIFT;
		break;
	case S_IFLNK:
		inode->i_op = &orangefs_symlink_inode_operations;
		break;
	case S_IFDIR:
		inode->i_op = &orangefs_dir_inode_operations;
		inode->i_fop = &orangefs_dir_operations;
		break;
	default:
		gossip_debug(GOSSIP_INODE_DEBUG,
			     "%s: unsupported mode\n",
			     __func__);
		return -EINVAL;
	}

	return 0;
}

/*
 * Given a ORANGEFS object identifier (fsid, handle), convert it into a ino_t type
 * that will be used as a hash-index from where the handle will
 * be searched for in the VFS hash table of inodes.
 */
static inline ino_t orangefs_handle_hash(struct orangefs_object_kref *ref)
{
	if (!ref)
		return 0;
	return orangefs_khandle_to_ino(&(ref->khandle));
}

/*
 * Called to set up an inode from iget5_locked.
 */
static int orangefs_set_inode(struct inode *inode, void *data)
{
	struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
	ORANGEFS_I(inode)->refn.fs_id = ref->fs_id;
	ORANGEFS_I(inode)->refn.khandle = ref->khandle;
	return 0;
}

/*
 * Called to determine if handles match.
 */
static int orangefs_test_inode(struct inode *inode, void *data)
{
	struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
	struct orangefs_inode_s *orangefs_inode = NULL;

	orangefs_inode = ORANGEFS_I(inode);
	return (!ORANGEFS_khandle_cmp(&(orangefs_inode->refn.khandle), &(ref->khandle))
		&& orangefs_inode->refn.fs_id == ref->fs_id);
}

/*
 * Front-end to lookup the inode-cache maintained by the VFS using the ORANGEFS
 * file handle.
 *
 * @sb: the file system super block instance.
 * @ref: The ORANGEFS object for which we are trying to locate an inode structure.
 */
struct inode *orangefs_iget(struct super_block *sb, struct orangefs_object_kref *ref)
{
	struct inode *inode = NULL;
	unsigned long hash;
	int error;

	hash = orangefs_handle_hash(ref);
	inode = iget5_locked(sb, hash, orangefs_test_inode, orangefs_set_inode, ref);
	if (!inode || !(inode->i_state & I_NEW))
		return inode;

	error = orangefs_inode_getattr(inode, 1, 0);
	if (error) {
		iget_failed(inode);
		return ERR_PTR(error);
	}

	inode->i_ino = hash;	/* needed for stat etc */
	orangefs_init_iops(inode);
	unlock_new_inode(inode);

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "iget handle %pU, fsid %d hash %ld i_ino %lu\n",
		     &ref->khandle,
		     ref->fs_id,
		     hash,
		     inode->i_ino);

	return inode;
}

/*
 * Allocate an inode for a newly created file and insert it into the inode hash.
 */
struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir,
		int mode, dev_t dev, struct orangefs_object_kref *ref)
{
	unsigned long hash = orangefs_handle_hash(ref);
	struct inode *inode;
	int error;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "%s:(sb is %p | MAJOR(dev)=%u | MINOR(dev)=%u mode=%o)\n",
		     __func__,
		     sb,
		     MAJOR(dev),
		     MINOR(dev),
		     mode);

	inode = new_inode(sb);
	if (!inode)
		return NULL;

	orangefs_set_inode(inode, ref);
	inode->i_ino = hash;	/* needed for stat etc */

	error = orangefs_inode_getattr(inode, 1, 0);
	if (error)
		goto out_iput;

	orangefs_init_iops(inode);

	inode->i_mode = mode;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	inode->i_size = PAGE_SIZE;
	inode->i_rdev = dev;

	error = insert_inode_locked4(inode, hash, orangefs_test_inode, ref);
	if (error < 0)
		goto out_iput;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "Initializing ACL's for inode %pU\n",
		     get_khandle_from_ino(inode));
	orangefs_init_acl(inode, dir);
	return inode;

out_iput:
	iput(inode);
	return ERR_PTR(error);
}