summaryrefslogtreecommitdiffstats
path: root/fs/orangefs/orangefs-utils.c
blob: 00fadaf0da8fb045dd18aff86faee0f052fc7689 (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
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
// SPDX-License-Identifier: GPL-2.0
/*
 * (C) 2001 Clemson University and The University of Chicago
 *
 * See COPYING in top-level directory.
 */
#include <linux/kernel.h>
#include "protocol.h"
#include "orangefs-kernel.h"
#include "orangefs-dev-proto.h"
#include "orangefs-bufmap.h"

__s32 fsid_of_op(struct orangefs_kernel_op_s *op)
{
	__s32 fsid = ORANGEFS_FS_ID_NULL;

	if (op) {
		switch (op->upcall.type) {
		case ORANGEFS_VFS_OP_FILE_IO:
			fsid = op->upcall.req.io.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_LOOKUP:
			fsid = op->upcall.req.lookup.parent_refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_CREATE:
			fsid = op->upcall.req.create.parent_refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_GETATTR:
			fsid = op->upcall.req.getattr.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_REMOVE:
			fsid = op->upcall.req.remove.parent_refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_MKDIR:
			fsid = op->upcall.req.mkdir.parent_refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_READDIR:
			fsid = op->upcall.req.readdir.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_SETATTR:
			fsid = op->upcall.req.setattr.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_SYMLINK:
			fsid = op->upcall.req.sym.parent_refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_RENAME:
			fsid = op->upcall.req.rename.old_parent_refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_STATFS:
			fsid = op->upcall.req.statfs.fs_id;
			break;
		case ORANGEFS_VFS_OP_TRUNCATE:
			fsid = op->upcall.req.truncate.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_RA_FLUSH:
			fsid = op->upcall.req.ra_cache_flush.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_FS_UMOUNT:
			fsid = op->upcall.req.fs_umount.fs_id;
			break;
		case ORANGEFS_VFS_OP_GETXATTR:
			fsid = op->upcall.req.getxattr.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_SETXATTR:
			fsid = op->upcall.req.setxattr.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_LISTXATTR:
			fsid = op->upcall.req.listxattr.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_REMOVEXATTR:
			fsid = op->upcall.req.removexattr.refn.fs_id;
			break;
		case ORANGEFS_VFS_OP_FSYNC:
			fsid = op->upcall.req.fsync.refn.fs_id;
			break;
		default:
			break;
		}
	}
	return fsid;
}

static int orangefs_inode_flags(struct ORANGEFS_sys_attr_s *attrs)
{
	int flags = 0;
	if (attrs->flags & ORANGEFS_IMMUTABLE_FL)
		flags |= S_IMMUTABLE;
	else
		flags &= ~S_IMMUTABLE;
	if (attrs->flags & ORANGEFS_APPEND_FL)
		flags |= S_APPEND;
	else
		flags &= ~S_APPEND;
	if (attrs->flags & ORANGEFS_NOATIME_FL)
		flags |= S_NOATIME;
	else
		flags &= ~S_NOATIME;
	return flags;
}

static int orangefs_inode_perms(struct ORANGEFS_sys_attr_s *attrs)
{
	int perm_mode = 0;

	if (attrs->perms & ORANGEFS_O_EXECUTE)
		perm_mode |= S_IXOTH;
	if (attrs->perms & ORANGEFS_O_WRITE)
		perm_mode |= S_IWOTH;
	if (attrs->perms & ORANGEFS_O_READ)
		perm_mode |= S_IROTH;

	if (attrs->perms & ORANGEFS_G_EXECUTE)
		perm_mode |= S_IXGRP;
	if (attrs->perms & ORANGEFS_G_WRITE)
		perm_mode |= S_IWGRP;
	if (attrs->perms & ORANGEFS_G_READ)
		perm_mode |= S_IRGRP;

	if (attrs->perms & ORANGEFS_U_EXECUTE)
		perm_mode |= S_IXUSR;
	if (attrs->perms & ORANGEFS_U_WRITE)
		perm_mode |= S_IWUSR;
	if (attrs->perms & ORANGEFS_U_READ)
		perm_mode |= S_IRUSR;

	if (attrs->perms & ORANGEFS_G_SGID)
		perm_mode |= S_ISGID;
	if (attrs->perms & ORANGEFS_U_SUID)
		perm_mode |= S_ISUID;

	return perm_mode;
}

/*
 * NOTE: in kernel land, we never use the sys_attr->link_target for
 * anything, so don't bother copying it into the sys_attr object here.
 */
static inline int copy_attributes_from_inode(struct inode *inode,
					     struct ORANGEFS_sys_attr_s *attrs,
					     struct iattr *iattr)
{
	umode_t tmp_mode;

	if (!iattr || !inode || !attrs) {
		gossip_err("NULL iattr (%p), inode (%p), attrs (%p) "
			   "in copy_attributes_from_inode!\n",
			   iattr,
			   inode,
			   attrs);
		return -EINVAL;
	}
	/*
	 * We need to be careful to only copy the attributes out of the
	 * iattr object that we know are valid.
	 */
	attrs->mask = 0;
	if (iattr->ia_valid & ATTR_UID) {
		attrs->owner = from_kuid(&init_user_ns, iattr->ia_uid);
		attrs->mask |= ORANGEFS_ATTR_SYS_UID;
		gossip_debug(GOSSIP_UTILS_DEBUG, "(UID) %d\n", attrs->owner);
	}
	if (iattr->ia_valid & ATTR_GID) {
		attrs->group = from_kgid(&init_user_ns, iattr->ia_gid);
		attrs->mask |= ORANGEFS_ATTR_SYS_GID;
		gossip_debug(GOSSIP_UTILS_DEBUG, "(GID) %d\n", attrs->group);
	}

	if (iattr->ia_valid & ATTR_ATIME) {
		attrs->mask |= ORANGEFS_ATTR_SYS_ATIME;
		if (iattr->ia_valid & ATTR_ATIME_SET) {
			attrs->atime = (time64_t)iattr->ia_atime.tv_sec;
			attrs->mask |= ORANGEFS_ATTR_SYS_ATIME_SET;
		}
	}
	if (iattr->ia_valid & ATTR_MTIME) {
		attrs->mask |= ORANGEFS_ATTR_SYS_MTIME;
		if (iattr->ia_valid & ATTR_MTIME_SET) {
			attrs->mtime = (time64_t)iattr->ia_mtime.tv_sec;
			attrs->mask |= ORANGEFS_ATTR_SYS_MTIME_SET;
		}
	}
	if (iattr->ia_valid & ATTR_CTIME)
		attrs->mask |= ORANGEFS_ATTR_SYS_CTIME;

	/*
	 * ORANGEFS cannot set size with a setattr operation.  Probably not likely
	 * to be requested through the VFS, but just in case, don't worry about
	 * ATTR_SIZE
	 */

	if (iattr->ia_valid & ATTR_MODE) {
		tmp_mode = iattr->ia_mode;
		if (tmp_mode & (S_ISVTX)) {
			if (is_root_handle(inode)) {
				/*
				 * allow sticky bit to be set on root (since
				 * it shows up that way by default anyhow),
				 * but don't show it to the server
				 */
				tmp_mode -= S_ISVTX;
			} else {
				gossip_debug(GOSSIP_UTILS_DEBUG,
					     "User attempted to set sticky bit on non-root directory; returning EINVAL.\n");
				return -EINVAL;
			}
		}

		if (tmp_mode & (S_ISUID)) {
			gossip_debug(GOSSIP_UTILS_DEBUG,
				     "Attempting to set setuid bit (not supported); returning EINVAL.\n");
			return -EINVAL;
		}

		attrs->perms = ORANGEFS_util_translate_mode(tmp_mode);
		attrs->mask |= ORANGEFS_ATTR_SYS_PERM;
	}

	return 0;
}

static int orangefs_inode_type(enum orangefs_ds_type objtype)
{
	if (objtype == ORANGEFS_TYPE_METAFILE)
		return S_IFREG;
	else if (objtype == ORANGEFS_TYPE_DIRECTORY)
		return S_IFDIR;
	else if (objtype == ORANGEFS_TYPE_SYMLINK)
		return S_IFLNK;
	else
		return -1;
}

static void orangefs_make_bad_inode(struct inode *inode)
{
	if (is_root_handle(inode)) {
		/*
		 * if this occurs, the pvfs2-client-core was killed but we
		 * can't afford to lose the inode operations and such
		 * associated with the root handle in any case.
		 */
		gossip_debug(GOSSIP_UTILS_DEBUG,
			     "*** NOT making bad root inode %pU\n",
			     get_khandle_from_ino(inode));
	} else {
		gossip_debug(GOSSIP_UTILS_DEBUG,
			     "*** making bad inode %pU\n",
			     get_khandle_from_ino(inode));
		make_bad_inode(inode);
	}
}

static int orangefs_inode_is_stale(struct inode *inode,
    struct ORANGEFS_sys_attr_s *attrs, char *link_target)
{
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
	int type = orangefs_inode_type(attrs->objtype);
	/*
	 * If the inode type or symlink target have changed then this
	 * inode is stale.
	 */
	if (type == -1 || !(inode->i_mode & type)) {
		orangefs_make_bad_inode(inode);
		return 1;
	}
	if (type == S_IFLNK && strncmp(orangefs_inode->link_target,
	    link_target, ORANGEFS_NAME_MAX)) {
		orangefs_make_bad_inode(inode);
		return 1;
	}
	return 0;
}

int orangefs_inode_getattr(struct inode *inode, int new, int bypass,
    u32 request_mask)
{
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
	struct orangefs_kernel_op_s *new_op;
	loff_t inode_size, rounded_up_size;
	int ret, type;

	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__,
	    get_khandle_from_ino(inode));

	if (!new && !bypass) {
		/*
		 * Must have all the attributes in the mask and be within cache
		 * time.
		 */
		if ((request_mask & orangefs_inode->getattr_mask) ==
		    request_mask &&
		    time_before(jiffies, orangefs_inode->getattr_time))
			return 0;
	}

	new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR);
	if (!new_op)
		return -ENOMEM;
	new_op->upcall.req.getattr.refn = orangefs_inode->refn;
	/*
	 * Size is the hardest attribute to get.  The incremental cost of any
	 * other attribute is essentially zero.
	 */
	if (request_mask & STATX_SIZE || new)
		new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_ALL_NOHINT;
	else
		new_op->upcall.req.getattr.mask =
		    ORANGEFS_ATTR_SYS_ALL_NOHINT & ~ORANGEFS_ATTR_SYS_SIZE;

	ret = service_operation(new_op, __func__,
	    get_interruptible_flag(inode));
	if (ret != 0)
		goto out;

	if (!new) {
		ret = orangefs_inode_is_stale(inode,
		    &new_op->downcall.resp.getattr.attributes,
		    new_op->downcall.resp.getattr.link_target);
		if (ret) {
			ret = -ESTALE;
			goto out;
		}
	}

	type = orangefs_inode_type(new_op->
	    downcall.resp.getattr.attributes.objtype);
	switch (type) {
	case S_IFREG:
		inode->i_flags = orangefs_inode_flags(&new_op->
		    downcall.resp.getattr.attributes);
		if (request_mask & STATX_SIZE || new) {
			inode_size = (loff_t)new_op->
			    downcall.resp.getattr.attributes.size;
			rounded_up_size =
			    (inode_size + (4096 - (inode_size % 4096)));
			inode->i_size = inode_size;
			orangefs_inode->blksize =
			    new_op->downcall.resp.getattr.attributes.blksize;
			spin_lock(&inode->i_lock);
			inode->i_bytes = inode_size;
			inode->i_blocks =
			    (unsigned long)(rounded_up_size / 512);
			spin_unlock(&inode->i_lock);
		}
		break;
	case S_IFDIR:
		if (request_mask & STATX_SIZE || new) {
			inode->i_size = PAGE_SIZE;
			orangefs_inode->blksize = i_blocksize(inode);
			spin_lock(&inode->i_lock);
			inode_set_bytes(inode, inode->i_size);
			spin_unlock(&inode->i_lock);
		}
		set_nlink(inode, 1);
		break;
	case S_IFLNK:
		if (new) {
			inode->i_size = (loff_t)strlen(new_op->
			    downcall.resp.getattr.link_target);
			orangefs_inode->blksize = i_blocksize(inode);
			ret = strscpy(orangefs_inode->link_target,
			    new_op->downcall.resp.getattr.link_target,
			    ORANGEFS_NAME_MAX);
			if (ret == -E2BIG) {
				ret = -EIO;
				goto out;
			}
			inode->i_link = orangefs_inode->link_target;
		}
		break;
	/* i.e. -1 */
	default:
		/* XXX: ESTALE?  This is what is done if it is not new. */
		orangefs_make_bad_inode(inode);
		ret = -ESTALE;
		goto out;
	}

	inode->i_uid = make_kuid(&init_user_ns, new_op->
	    downcall.resp.getattr.attributes.owner);
	inode->i_gid = make_kgid(&init_user_ns, new_op->
	    downcall.resp.getattr.attributes.group);
	inode->i_atime.tv_sec = (time64_t)new_op->
	    downcall.resp.getattr.attributes.atime;
	inode->i_mtime.tv_sec = (time64_t)new_op->
	    downcall.resp.getattr.attributes.mtime;
	inode->i_ctime.tv_sec = (time64_t)new_op->
	    downcall.resp.getattr.attributes.ctime;
	inode->i_atime.tv_nsec = 0;
	inode->i_mtime.tv_nsec = 0;
	inode->i_ctime.tv_nsec = 0;

	/* special case: mark the root inode as sticky */
	inode->i_mode = type | (is_root_handle(inode) ? S_ISVTX : 0) |
	    orangefs_inode_perms(&new_op->downcall.resp.getattr.attributes);

	orangefs_inode->getattr_time = jiffies +
	    orangefs_getattr_timeout_msecs*HZ/1000;
	if (request_mask & STATX_SIZE || new)
		orangefs_inode->getattr_mask = STATX_BASIC_STATS;
	else
		orangefs_inode->getattr_mask = STATX_BASIC_STATS & ~STATX_SIZE;
	ret = 0;
out:
	op_release(new_op);
	return ret;
}

int orangefs_inode_check_changed(struct inode *inode)
{
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
	struct orangefs_kernel_op_s *new_op;
	int ret;

	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__,
	    get_khandle_from_ino(inode));

	new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR);
	if (!new_op)
		return -ENOMEM;
	new_op->upcall.req.getattr.refn = orangefs_inode->refn;
	new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_TYPE |
	    ORANGEFS_ATTR_SYS_LNK_TARGET;

	ret = service_operation(new_op, __func__,
	    get_interruptible_flag(inode));
	if (ret != 0)
		goto out;

	ret = orangefs_inode_is_stale(inode,
	    &new_op->downcall.resp.getattr.attributes,
	    new_op->downcall.resp.getattr.link_target);
out:
	op_release(new_op);
	return ret;
}

/*
 * issues a orangefs setattr request to make sure the new attribute values
 * take effect if successful.  returns 0 on success; -errno otherwise
 */
int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr)
{
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
	struct orangefs_kernel_op_s *new_op;
	int ret;

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

	new_op->upcall.req.setattr.refn = orangefs_inode->refn;
	ret = copy_attributes_from_inode(inode,
		       &new_op->upcall.req.setattr.attributes,
		       iattr);
	if (ret >= 0) {
		ret = service_operation(new_op, __func__,
				get_interruptible_flag(inode));

		gossip_debug(GOSSIP_UTILS_DEBUG,
			     "orangefs_inode_setattr: returning %d\n",
			     ret);
	}

	op_release(new_op);

	if (ret == 0)
		orangefs_inode->getattr_time = jiffies - 1;

	return ret;
}

/*
 * The following is a very dirty hack that is now a permanent part of the
 * ORANGEFS protocol. See protocol.h for more error definitions.
 */

/* The order matches include/orangefs-types.h in the OrangeFS source. */
static int PINT_errno_mapping[] = {
	0, EPERM, ENOENT, EINTR, EIO, ENXIO, EBADF, EAGAIN, ENOMEM,
	EFAULT, EBUSY, EEXIST, ENODEV, ENOTDIR, EISDIR, EINVAL, EMFILE,
	EFBIG, ENOSPC, EROFS, EMLINK, EPIPE, EDEADLK, ENAMETOOLONG,
	ENOLCK, ENOSYS, ENOTEMPTY, ELOOP, EWOULDBLOCK, ENOMSG, EUNATCH,
	EBADR, EDEADLOCK, ENODATA, ETIME, ENONET, EREMOTE, ECOMM,
	EPROTO, EBADMSG, EOVERFLOW, ERESTART, EMSGSIZE, EPROTOTYPE,
	ENOPROTOOPT, EPROTONOSUPPORT, EOPNOTSUPP, EADDRINUSE,
	EADDRNOTAVAIL, ENETDOWN, ENETUNREACH, ENETRESET, ENOBUFS,
	ETIMEDOUT, ECONNREFUSED, EHOSTDOWN, EHOSTUNREACH, EALREADY,
	EACCES, ECONNRESET, ERANGE
};

int orangefs_normalize_to_errno(__s32 error_code)
{
	__u32 i;

	/* Success */
	if (error_code == 0) {
		return 0;
	/*
	 * This shouldn't ever happen. If it does it should be fixed on the
	 * server.
	 */
	} else if (error_code > 0) {
		gossip_err("orangefs: error status received.\n");
		gossip_err("orangefs: assuming error code is inverted.\n");
		error_code = -error_code;
	}

	/*
	 * XXX: This is very bad since error codes from ORANGEFS may not be
	 * suitable for return into userspace.
	 */

	/*
	 * Convert ORANGEFS error values into errno values suitable for return
	 * from the kernel.
	 */
	if ((-error_code) & ORANGEFS_NON_ERRNO_ERROR_BIT) {
		if (((-error_code) &
		    (ORANGEFS_ERROR_NUMBER_BITS|ORANGEFS_NON_ERRNO_ERROR_BIT|
		    ORANGEFS_ERROR_BIT)) == ORANGEFS_ECANCEL) {
			/*
			 * cancellation error codes generally correspond to
			 * a timeout from the client's perspective
			 */
			error_code = -ETIMEDOUT;
		} else {
			/* assume a default error code */
			gossip_err("orangefs: warning: got error code without errno equivalent: %d.\n", error_code);
			error_code = -EINVAL;
		}

	/* Convert ORANGEFS encoded errno values into regular errno values. */
	} else if ((-error_code) & ORANGEFS_ERROR_BIT) {
		i = (-error_code) & ~(ORANGEFS_ERROR_BIT|ORANGEFS_ERROR_CLASS_BITS);
		if (i < ARRAY_SIZE(PINT_errno_mapping))
			error_code = -PINT_errno_mapping[i];
		else
			error_code = -EINVAL;

	/*
	 * Only ORANGEFS protocol error codes should ever come here. Otherwise
	 * there is a bug somewhere.
	 */
	} else {
		gossip_err("orangefs: orangefs_normalize_to_errno: got error code which is not from ORANGEFS.\n");
		error_code = -EINVAL;
	}
	return error_code;
}

#define NUM_MODES 11
__s32 ORANGEFS_util_translate_mode(int mode)
{
	int ret = 0;
	int i = 0;
	static int modes[NUM_MODES] = {
		S_IXOTH, S_IWOTH, S_IROTH,
		S_IXGRP, S_IWGRP, S_IRGRP,
		S_IXUSR, S_IWUSR, S_IRUSR,
		S_ISGID, S_ISUID
	};
	static int orangefs_modes[NUM_MODES] = {
		ORANGEFS_O_EXECUTE, ORANGEFS_O_WRITE, ORANGEFS_O_READ,
		ORANGEFS_G_EXECUTE, ORANGEFS_G_WRITE, ORANGEFS_G_READ,
		ORANGEFS_U_EXECUTE, ORANGEFS_U_WRITE, ORANGEFS_U_READ,
		ORANGEFS_G_SGID, ORANGEFS_U_SUID
	};

	for (i = 0; i < NUM_MODES; i++)
		if (mode & modes[i])
			ret |= orangefs_modes[i];

	return ret;
}
#undef NUM_MODES