summaryrefslogtreecommitdiff
path: root/fs/orangefs/file.c
blob: d8c97b87bf265f99acd4ccdfb65214702b68cbe0 (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
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
// SPDX-License-Identifier: GPL-2.0
/*
 * (C) 2001 Clemson University and The University of Chicago
 * Copyright 2018 Omnibond Systems, L.L.C.
 *
 * See COPYING in top-level directory.
 */

/*
 *  Linux VFS file operations.
 */

#include "protocol.h"
#include "orangefs-kernel.h"
#include "orangefs-bufmap.h"
#include <linux/fs.h>
#include <linux/pagemap.h>

static int flush_racache(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: %pU: Handle is %pU | fs_id %d\n", __func__,
	    get_khandle_from_ino(inode), &orangefs_inode->refn.khandle,
	    orangefs_inode->refn.fs_id);

	new_op = op_alloc(ORANGEFS_VFS_OP_RA_FLUSH);
	if (!new_op)
		return -ENOMEM;
	new_op->upcall.req.ra_cache_flush.refn = orangefs_inode->refn;

	ret = service_operation(new_op, "orangefs_flush_racache",
	    get_interruptible_flag(inode));

	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: got return value of %d\n",
	    __func__, ret);

	op_release(new_op);
	return ret;
}

/*
 * Post and wait for the I/O upcall to finish
 */
ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode,
		loff_t *offset, struct iov_iter *iter,
		size_t total_size, loff_t readahead_size)
{
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
	struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
	struct orangefs_kernel_op_s *new_op = NULL;
	int buffer_index = -1;
	ssize_t ret;

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

	/* synchronous I/O */
	new_op->upcall.req.io.readahead_size = readahead_size;
	new_op->upcall.req.io.io_type = type;
	new_op->upcall.req.io.refn = orangefs_inode->refn;

populate_shared_memory:
	/* get a shared buffer index */
	buffer_index = orangefs_bufmap_get();
	if (buffer_index < 0) {
		ret = buffer_index;
		gossip_debug(GOSSIP_FILE_DEBUG,
			     "%s: orangefs_bufmap_get failure (%zd)\n",
			     __func__, ret);
		goto out;
	}
	gossip_debug(GOSSIP_FILE_DEBUG,
		     "%s(%pU): GET op %p -> buffer_index %d\n",
		     __func__,
		     handle,
		     new_op,
		     buffer_index);

	new_op->uses_shared_memory = 1;
	new_op->upcall.req.io.buf_index = buffer_index;
	new_op->upcall.req.io.count = total_size;
	new_op->upcall.req.io.offset = *offset;

	gossip_debug(GOSSIP_FILE_DEBUG,
		     "%s(%pU): offset: %llu total_size: %zd\n",
		     __func__,
		     handle,
		     llu(*offset),
		     total_size);
	/*
	 * Stage 1: copy the buffers into client-core's address space
	 */
	if (type == ORANGEFS_IO_WRITE && total_size) {
		ret = orangefs_bufmap_copy_from_iovec(iter, buffer_index,
		    total_size);
		if (ret < 0) {
			gossip_err("%s: Failed to copy-in buffers. Please make sure that the pvfs2-client is running. %ld\n",
			    __func__, (long)ret);
			goto out;
		}
	}

	gossip_debug(GOSSIP_FILE_DEBUG,
		     "%s(%pU): Calling post_io_request with tag (%llu)\n",
		     __func__,
		     handle,
		     llu(new_op->tag));

	/* Stage 2: Service the I/O operation */
	ret = service_operation(new_op,
				type == ORANGEFS_IO_WRITE ?
					"file_write" :
					"file_read",
				get_interruptible_flag(inode));

	/*
	 * If service_operation() returns -EAGAIN #and# the operation was
	 * purged from orangefs_request_list or htable_ops_in_progress, then
	 * we know that the client was restarted, causing the shared memory
	 * area to be wiped clean.  To restart a  write operation in this
	 * case, we must re-copy the data from the user's iovec to a NEW
	 * shared memory location. To restart a read operation, we must get
	 * a new shared memory location.
	 */
	if (ret == -EAGAIN && op_state_purged(new_op)) {
		orangefs_bufmap_put(buffer_index);
		buffer_index = -1;
		if (type == ORANGEFS_IO_WRITE)
			iov_iter_revert(iter, total_size);
		gossip_debug(GOSSIP_FILE_DEBUG,
			     "%s:going to repopulate_shared_memory.\n",
			     __func__);
		goto populate_shared_memory;
	}

	if (ret < 0) {
		if (ret == -EINTR) {
			/*
			 * We can't return EINTR if any data was written,
			 * it's not POSIX. It is minimally acceptable
			 * to give a partial write, the way NFS does.
			 *
			 * It would be optimal to return all or nothing,
			 * but if a userspace write is bigger than
			 * an IO buffer, and the interrupt occurs
			 * between buffer writes, that would not be
			 * possible.
			 */
			switch (new_op->op_state - OP_VFS_STATE_GIVEN_UP) {
			/*
			 * If the op was waiting when the interrupt
			 * occurred, then the client-core did not
			 * trigger the write.
			 */
			case OP_VFS_STATE_WAITING:
				if (*offset == 0)
					ret = -EINTR;
				else
					ret = 0;
				break;
			/*
			 * If the op was in progress when the interrupt
			 * occurred, then the client-core was able to
			 * trigger the write.
			 */
			case OP_VFS_STATE_INPROGR:
				ret = total_size;
				break;
			default:
				gossip_err("%s: unexpected op state :%d:.\n",
					   __func__,
					   new_op->op_state);
				ret = 0;
				break;
			}
			gossip_debug(GOSSIP_FILE_DEBUG,
				     "%s: got EINTR, state:%d: %p\n",
				     __func__,
				     new_op->op_state,
				     new_op);
		} else {
			gossip_err("%s: error in %s handle %pU, returning %zd\n",
				__func__,
				type == ORANGEFS_IO_READ ?
					"read from" : "write to",
				handle, ret);
		}
		if (orangefs_cancel_op_in_progress(new_op))
			return ret;

		goto out;
	}

	/*
	 * Stage 3: Post copy buffers from client-core's address space
	 */
	if (type == ORANGEFS_IO_READ && new_op->downcall.resp.io.amt_complete) {
		/*
		 * NOTE: the iovector can either contain addresses which
		 *       can futher be kernel-space or user-space addresses.
		 *       or it can pointers to struct page's
		 */
		ret = orangefs_bufmap_copy_to_iovec(iter, buffer_index,
		    new_op->downcall.resp.io.amt_complete);
		if (ret < 0) {
			gossip_err("%s: Failed to copy-out buffers. Please make sure that the pvfs2-client is running (%ld)\n",
			    __func__, (long)ret);
			goto out;
		}
	}
	gossip_debug(GOSSIP_FILE_DEBUG,
	    "%s(%pU): Amount %s, returned by the sys-io call:%d\n",
	    __func__,
	    handle,
	    type == ORANGEFS_IO_READ ?  "read" : "written",
	    (int)new_op->downcall.resp.io.amt_complete);

	ret = new_op->downcall.resp.io.amt_complete;

out:
	if (buffer_index >= 0) {
		orangefs_bufmap_put(buffer_index);
		gossip_debug(GOSSIP_FILE_DEBUG,
			     "%s(%pU): PUT buffer_index %d\n",
			     __func__, handle, buffer_index);
		buffer_index = -1;
	}
	op_release(new_op);
	return ret;
}

/*
 * Common entry point for read/write/readv/writev
 * This function will dispatch it to either the direct I/O
 * or buffered I/O path depending on the mount options and/or
 * augmented/extended metadata attached to the file.
 * Note: File extended attributes override any mount options.
 */
ssize_t do_readv_writev(enum ORANGEFS_io_type type, struct file *file,
		loff_t *offset, struct iov_iter *iter)
{
	struct inode *inode = file->f_mapping->host;
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
	struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
	size_t count = iov_iter_count(iter);
	ssize_t total_count = 0;
	ssize_t ret = -EINVAL;

	gossip_debug(GOSSIP_FILE_DEBUG,
		"%s-BEGIN(%pU): count(%d) after estimate_max_iovecs.\n",
		__func__,
		handle,
		(int)count);

	if (type == ORANGEFS_IO_WRITE) {
		gossip_debug(GOSSIP_FILE_DEBUG,
			     "%s(%pU): proceeding with offset : %llu, "
			     "size %d\n",
			     __func__,
			     handle,
			     llu(*offset),
			     (int)count);
	}

	if (count == 0) {
		ret = 0;
		goto out;
	}

	while (iov_iter_count(iter)) {
		size_t each_count = iov_iter_count(iter);
		size_t amt_complete;

		/* how much to transfer in this loop iteration */
		if (each_count > orangefs_bufmap_size_query())
			each_count = orangefs_bufmap_size_query();

		gossip_debug(GOSSIP_FILE_DEBUG,
			     "%s(%pU): size of each_count(%d)\n",
			     __func__,
			     handle,
			     (int)each_count);
		gossip_debug(GOSSIP_FILE_DEBUG,
			     "%s(%pU): BEFORE wait_for_io: offset is %d\n",
			     __func__,
			     handle,
			     (int)*offset);

		ret = wait_for_direct_io(type, inode, offset, iter,
				each_count, 0);
		gossip_debug(GOSSIP_FILE_DEBUG,
			     "%s(%pU): return from wait_for_io:%d\n",
			     __func__,
			     handle,
			     (int)ret);

		if (ret < 0)
			goto out;

		*offset += ret;
		total_count += ret;
		amt_complete = ret;

		gossip_debug(GOSSIP_FILE_DEBUG,
			     "%s(%pU): AFTER wait_for_io: offset is %d\n",
			     __func__,
			     handle,
			     (int)*offset);

		/*
		 * if we got a short I/O operations,
		 * fall out and return what we got so far
		 */
		if (amt_complete < each_count)
			break;
	} /*end while */

out:
	if (total_count > 0)
		ret = total_count;
	if (ret > 0) {
		if (type == ORANGEFS_IO_READ) {
			file_accessed(file);
		} else {
			file_update_time(file);
			if (*offset > i_size_read(inode))
				i_size_write(inode, *offset);
		}
	}

	gossip_debug(GOSSIP_FILE_DEBUG,
		     "%s(%pU): Value(%d) returned.\n",
		     __func__,
		     handle,
		     (int)ret);

	return ret;
}

static ssize_t orangefs_file_read_iter(struct kiocb *iocb,
    struct iov_iter *iter)
{
	orangefs_stats.reads++;
	return generic_file_read_iter(iocb, iter);
}

static ssize_t orangefs_file_write_iter(struct kiocb *iocb,
    struct iov_iter *iter)
{
	orangefs_stats.writes++;
	return generic_file_write_iter(iocb, iter);
}

/*
 * Perform a miscellaneous operation on a file.
 */
static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	int ret = -ENOTTY;
	__u64 val = 0;
	unsigned long uval;

	gossip_debug(GOSSIP_FILE_DEBUG,
		     "orangefs_ioctl: called with cmd %d\n",
		     cmd);

	/*
	 * we understand some general ioctls on files, such as the immutable
	 * and append flags
	 */
	if (cmd == FS_IOC_GETFLAGS) {
		val = 0;
		ret = orangefs_inode_getxattr(file_inode(file),
					      "user.pvfs2.meta_hint",
					      &val, sizeof(val));
		if (ret < 0 && ret != -ENODATA)
			return ret;
		else if (ret == -ENODATA)
			val = 0;
		uval = val;
		gossip_debug(GOSSIP_FILE_DEBUG,
			     "orangefs_ioctl: FS_IOC_GETFLAGS: %llu\n",
			     (unsigned long long)uval);
		return put_user(uval, (int __user *)arg);
	} else if (cmd == FS_IOC_SETFLAGS) {
		ret = 0;
		if (get_user(uval, (int __user *)arg))
			return -EFAULT;
		/*
		 * ORANGEFS_MIRROR_FL is set internally when the mirroring mode
		 * is turned on for a file. The user is not allowed to turn
		 * on this bit, but the bit is present if the user first gets
		 * the flags and then updates the flags with some new
		 * settings. So, we ignore it in the following edit. bligon.
		 */
		if ((uval & ~ORANGEFS_MIRROR_FL) &
		    (~(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NOATIME_FL))) {
			gossip_err("orangefs_ioctl: the FS_IOC_SETFLAGS only supports setting one of FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NOATIME_FL\n");
			return -EINVAL;
		}
		val = uval;
		gossip_debug(GOSSIP_FILE_DEBUG,
			     "orangefs_ioctl: FS_IOC_SETFLAGS: %llu\n",
			     (unsigned long long)val);
		ret = orangefs_inode_setxattr(file_inode(file),
					      "user.pvfs2.meta_hint",
					      &val, sizeof(val), 0);
	}

	return ret;
}

static vm_fault_t orangefs_fault(struct vm_fault *vmf)
{
	struct file *file = vmf->vma->vm_file;
	int ret;
	ret = orangefs_inode_getattr(file->f_mapping->host,
	    ORANGEFS_GETATTR_SIZE);
	if (ret == -ESTALE)
		ret = -EIO;
	if (ret) {
		gossip_err("%s: orangefs_inode_getattr failed, "
		    "ret:%d:.\n", __func__, ret);
		return VM_FAULT_SIGBUS;
	}
	return filemap_fault(vmf);
}

static const struct vm_operations_struct orangefs_file_vm_ops = {
	.fault = orangefs_fault,
	.map_pages = filemap_map_pages,
	.page_mkwrite = filemap_page_mkwrite,
};

/*
 * Memory map a region of a file.
 */
static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	gossip_debug(GOSSIP_FILE_DEBUG,
		     "orangefs_file_mmap: called on %s\n",
		     (file ?
			(char *)file->f_path.dentry->d_name.name :
			(char *)"Unknown"));

	/* set the sequential readahead hint */
	vma->vm_flags |= VM_SEQ_READ;
	vma->vm_flags &= ~VM_RAND_READ;

	file_accessed(file);
	vma->vm_ops = &orangefs_file_vm_ops;
	return 0;
}

#define mapping_nrpages(idata) ((idata)->nrpages)

/*
 * Called to notify the module that there are no more references to
 * this file (i.e. no processes have it open).
 *
 * \note Not called when each file is closed.
 */
static int orangefs_file_release(struct inode *inode, struct file *file)
{
	gossip_debug(GOSSIP_FILE_DEBUG,
		     "orangefs_file_release: called on %pD\n",
		     file);

	/*
	 * remove all associated inode pages from the page cache and
	 * readahead cache (if any); this forces an expensive refresh of
	 * data for the next caller of mmap (or 'get_block' accesses)
	 */
	if (file_inode(file) &&
	    file_inode(file)->i_mapping &&
	    mapping_nrpages(&file_inode(file)->i_data)) {
		if (orangefs_features & ORANGEFS_FEATURE_READAHEAD) {
			gossip_debug(GOSSIP_INODE_DEBUG,
			    "calling flush_racache on %pU\n",
			    get_khandle_from_ino(inode));
			flush_racache(inode);
			gossip_debug(GOSSIP_INODE_DEBUG,
			    "flush_racache finished\n");
		}
	}
	return 0;
}

/*
 * Push all data for a specific file onto permanent storage.
 */
static int orangefs_fsync(struct file *file,
		       loff_t start,
		       loff_t end,
		       int datasync)
{
	int ret;
	struct orangefs_inode_s *orangefs_inode =
		ORANGEFS_I(file_inode(file));
	struct orangefs_kernel_op_s *new_op = NULL;

	ret = filemap_write_and_wait_range(file_inode(file)->i_mapping,
	    start, end);
	if (ret < 0)
		return ret;

	new_op = op_alloc(ORANGEFS_VFS_OP_FSYNC);
	if (!new_op)
		return -ENOMEM;
	new_op->upcall.req.fsync.refn = orangefs_inode->refn;

	ret = service_operation(new_op,
			"orangefs_fsync",
			get_interruptible_flag(file_inode(file)));

	gossip_debug(GOSSIP_FILE_DEBUG,
		     "orangefs_fsync got return value of %d\n",
		     ret);

	op_release(new_op);
	return ret;
}

/*
 * Change the file pointer position for an instance of an open file.
 *
 * \note If .llseek is overriden, we must acquire lock as described in
 *       Documentation/filesystems/Locking.
 *
 * Future upgrade could support SEEK_DATA and SEEK_HOLE but would
 * require much changes to the FS
 */
static loff_t orangefs_file_llseek(struct file *file, loff_t offset, int origin)
{
	int ret = -EINVAL;
	struct inode *inode = file_inode(file);

	if (origin == SEEK_END) {
		/*
		 * revalidate the inode's file size.
		 * NOTE: We are only interested in file size here,
		 * so we set mask accordingly.
		 */
		ret = orangefs_inode_getattr(file->f_mapping->host,
		    ORANGEFS_GETATTR_SIZE);
		if (ret == -ESTALE)
			ret = -EIO;
		if (ret) {
			gossip_debug(GOSSIP_FILE_DEBUG,
				     "%s:%s:%d calling make bad inode\n",
				     __FILE__,
				     __func__,
				     __LINE__);
			return ret;
		}
	}

	gossip_debug(GOSSIP_FILE_DEBUG,
		     "orangefs_file_llseek: offset is %ld | origin is %d"
		     " | inode size is %lu\n",
		     (long)offset,
		     origin,
		     (unsigned long)i_size_read(inode));

	return generic_file_llseek(file, offset, origin);
}

/*
 * Support local locks (locks that only this kernel knows about)
 * if Orangefs was mounted -o local_lock.
 */
static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl)
{
	int rc = -EINVAL;

	if (ORANGEFS_SB(file_inode(filp)->i_sb)->flags & ORANGEFS_OPT_LOCAL_LOCK) {
		if (cmd == F_GETLK) {
			rc = 0;
			posix_test_lock(filp, fl);
		} else {
			rc = posix_lock_file(filp, fl, NULL);
		}
	}

	return rc;
}

static int orangefs_flush(struct file *file, fl_owner_t id)
{
	return vfs_fsync(file, 0);
}

/** ORANGEFS implementation of VFS file operations */
const struct file_operations orangefs_file_operations = {
	.llseek		= orangefs_file_llseek,
	.read_iter	= orangefs_file_read_iter,
	.write_iter	= orangefs_file_write_iter,
	.lock		= orangefs_lock,
	.unlocked_ioctl	= orangefs_ioctl,
	.mmap		= orangefs_file_mmap,
	.open		= generic_file_open,
	.flush		= orangefs_flush,
	.release	= orangefs_file_release,
	.fsync		= orangefs_fsync,
};