summaryrefslogtreecommitdiff
path: root/fs/nfs/nfs4filelayout.c
blob: 42855846481781cd7d2bc04b631ab8f2334317bb (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
/*
 *  Module for the pnfs nfs4 file layout driver.
 *  Defines all I/O and Policy interface operations, plus code
 *  to register itself with the pNFS client.
 *
 *  Copyright (c) 2002
 *  The Regents of the University of Michigan
 *  All Rights Reserved
 *
 *  Dean Hildebrand <dhildebz@umich.edu>
 *
 *  Permission is granted to use, copy, create derivative works, and
 *  redistribute this software and such derivative works for any purpose,
 *  so long as the name of the University of Michigan is not used in
 *  any advertising or publicity pertaining to the use or distribution
 *  of this software without specific, written prior authorization. If
 *  the above copyright notice or any other identification of the
 *  University of Michigan is included in any copy of any portion of
 *  this software, then the disclaimer below must also be included.
 *
 *  This software is provided as is, without representation or warranty
 *  of any kind either express or implied, including without limitation
 *  the implied warranties of merchantability, fitness for a particular
 *  purpose, or noninfringement.  The Regents of the University of
 *  Michigan shall not be liable for any damages, including special,
 *  indirect, incidental, or consequential damages, with respect to any
 *  claim arising out of or in connection with the use of the software,
 *  even if it has been or is hereafter advised of the possibility of
 *  such damages.
 */

#include <linux/nfs_fs.h>

#include "internal.h"
#include "nfs4filelayout.h"

#define NFSDBG_FACILITY         NFSDBG_PNFS_LD

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Dean Hildebrand <dhildebz@umich.edu>");
MODULE_DESCRIPTION("The NFSv4 file layout driver");

#define FILELAYOUT_POLL_RETRY_MAX     (15*HZ)

static loff_t
filelayout_get_dense_offset(struct nfs4_filelayout_segment *flseg,
			    loff_t offset)
{
	u32 stripe_width = flseg->stripe_unit * flseg->dsaddr->stripe_count;
	u64 tmp;

	offset -= flseg->pattern_offset;
	tmp = offset;
	do_div(tmp, stripe_width);

	return tmp * flseg->stripe_unit + do_div(offset, flseg->stripe_unit);
}

/* This function is used by the layout driver to calculate the
 * offset of the file on the dserver based on whether the
 * layout type is STRIPE_DENSE or STRIPE_SPARSE
 */
static loff_t
filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
{
	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);

	switch (flseg->stripe_type) {
	case STRIPE_SPARSE:
		return offset;

	case STRIPE_DENSE:
		return filelayout_get_dense_offset(flseg, offset);
	}

	BUG();
}

/* For data server errors we don't recover from */
static void
filelayout_set_lo_fail(struct pnfs_layout_segment *lseg)
{
	if (lseg->pls_range.iomode == IOMODE_RW) {
		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
	} else {
		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
	}
}

static int filelayout_async_handle_error(struct rpc_task *task,
					 struct nfs4_state *state,
					 struct nfs_client *clp,
					 int *reset)
{
	if (task->tk_status >= 0)
		return 0;

	*reset = 0;

	switch (task->tk_status) {
	case -NFS4ERR_BADSESSION:
	case -NFS4ERR_BADSLOT:
	case -NFS4ERR_BAD_HIGH_SLOT:
	case -NFS4ERR_DEADSESSION:
	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
	case -NFS4ERR_SEQ_FALSE_RETRY:
	case -NFS4ERR_SEQ_MISORDERED:
		dprintk("%s ERROR %d, Reset session. Exchangeid "
			"flags 0x%x\n", __func__, task->tk_status,
			clp->cl_exchange_flags);
		nfs4_schedule_session_recovery(clp->cl_session);
		break;
	case -NFS4ERR_DELAY:
	case -NFS4ERR_GRACE:
	case -EKEYEXPIRED:
		rpc_delay(task, FILELAYOUT_POLL_RETRY_MAX);
		break;
	default:
		dprintk("%s DS error. Retry through MDS %d\n", __func__,
			task->tk_status);
		*reset = 1;
		break;
	}
	task->tk_status = 0;
	return -EAGAIN;
}

/* NFS_PROTO call done callback routines */

static int filelayout_read_done_cb(struct rpc_task *task,
				struct nfs_read_data *data)
{
	struct nfs_client *clp = data->ds_clp;
	int reset = 0;

	dprintk("%s DS read\n", __func__);

	if (filelayout_async_handle_error(task, data->args.context->state,
					  data->ds_clp, &reset) == -EAGAIN) {
		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
			__func__, data->ds_clp, data->ds_clp->cl_session);
		if (reset) {
			filelayout_set_lo_fail(data->lseg);
			nfs4_reset_read(task, data);
			clp = NFS_SERVER(data->inode)->nfs_client;
		}
		nfs_restart_rpc(task, clp);
		return -EAGAIN;
	}

	return 0;
}

/*
 * Call ops for the async read/write cases
 * In the case of dense layouts, the offset needs to be reset to its
 * original value.
 */
static void filelayout_read_prepare(struct rpc_task *task, void *data)
{
	struct nfs_read_data *rdata = (struct nfs_read_data *)data;

	rdata->read_done_cb = filelayout_read_done_cb;

	if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
				&rdata->args.seq_args, &rdata->res.seq_res,
				0, task))
		return;

	rpc_call_start(task);
}

static void filelayout_read_call_done(struct rpc_task *task, void *data)
{
	struct nfs_read_data *rdata = (struct nfs_read_data *)data;

	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);

	/* Note this may cause RPC to be resent */
	rdata->mds_ops->rpc_call_done(task, data);
}

static void filelayout_read_release(void *data)
{
	struct nfs_read_data *rdata = (struct nfs_read_data *)data;

	rdata->mds_ops->rpc_release(data);
}

static int filelayout_write_done_cb(struct rpc_task *task,
				struct nfs_write_data *data)
{
	int reset = 0;

	if (filelayout_async_handle_error(task, data->args.context->state,
					  data->ds_clp, &reset) == -EAGAIN) {
		struct nfs_client *clp;

		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
			__func__, data->ds_clp, data->ds_clp->cl_session);
		if (reset) {
			filelayout_set_lo_fail(data->lseg);
			nfs4_reset_write(task, data);
			clp = NFS_SERVER(data->inode)->nfs_client;
		} else
			clp = data->ds_clp;
		nfs_restart_rpc(task, clp);
		return -EAGAIN;
	}

	return 0;
}

static void filelayout_write_prepare(struct rpc_task *task, void *data)
{
	struct nfs_write_data *wdata = (struct nfs_write_data *)data;

	if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
				&wdata->args.seq_args, &wdata->res.seq_res,
				0, task))
		return;

	rpc_call_start(task);
}

static void filelayout_write_call_done(struct rpc_task *task, void *data)
{
	struct nfs_write_data *wdata = (struct nfs_write_data *)data;

	/* Note this may cause RPC to be resent */
	wdata->mds_ops->rpc_call_done(task, data);
}

static void filelayout_write_release(void *data)
{
	struct nfs_write_data *wdata = (struct nfs_write_data *)data;

	wdata->mds_ops->rpc_release(data);
}

struct rpc_call_ops filelayout_read_call_ops = {
	.rpc_call_prepare = filelayout_read_prepare,
	.rpc_call_done = filelayout_read_call_done,
	.rpc_release = filelayout_read_release,
};

struct rpc_call_ops filelayout_write_call_ops = {
	.rpc_call_prepare = filelayout_write_prepare,
	.rpc_call_done = filelayout_write_call_done,
	.rpc_release = filelayout_write_release,
};

static enum pnfs_try_status
filelayout_read_pagelist(struct nfs_read_data *data)
{
	struct pnfs_layout_segment *lseg = data->lseg;
	struct nfs4_pnfs_ds *ds;
	loff_t offset = data->args.offset;
	u32 j, idx;
	struct nfs_fh *fh;
	int status;

	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
		__func__, data->inode->i_ino,
		data->args.pgbase, (size_t)data->args.count, offset);

	/* Retrieve the correct rpc_client for the byte range */
	j = nfs4_fl_calc_j_index(lseg, offset);
	idx = nfs4_fl_calc_ds_index(lseg, j);
	ds = nfs4_fl_prepare_ds(lseg, idx);
	if (!ds) {
		/* Either layout fh index faulty, or ds connect failed */
		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
		return PNFS_NOT_ATTEMPTED;
	}
	dprintk("%s USE DS:ip %x %hu\n", __func__,
		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));

	/* No multipath support. Use first DS */
	data->ds_clp = ds->ds_clp;
	fh = nfs4_fl_select_ds_fh(lseg, j);
	if (fh)
		data->args.fh = fh;

	data->args.offset = filelayout_get_dserver_offset(lseg, offset);
	data->mds_offset = offset;

	/* Perform an asynchronous read to ds */
	status = nfs_initiate_read(data, ds->ds_clp->cl_rpcclient,
				   &filelayout_read_call_ops);
	BUG_ON(status != 0);
	return PNFS_ATTEMPTED;
}

/* Perform async writes. */
static enum pnfs_try_status
filelayout_write_pagelist(struct nfs_write_data *data, int sync)
{
	struct pnfs_layout_segment *lseg = data->lseg;
	struct nfs4_pnfs_ds *ds;
	loff_t offset = data->args.offset;
	u32 j, idx;
	struct nfs_fh *fh;
	int status;

	/* Retrieve the correct rpc_client for the byte range */
	j = nfs4_fl_calc_j_index(lseg, offset);
	idx = nfs4_fl_calc_ds_index(lseg, j);
	ds = nfs4_fl_prepare_ds(lseg, idx);
	if (!ds) {
		printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
		return PNFS_NOT_ATTEMPTED;
	}
	dprintk("%s ino %lu sync %d req %Zu@%llu DS:%x:%hu\n", __func__,
		data->inode->i_ino, sync, (size_t) data->args.count, offset,
		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));

	/* We can't handle commit to ds yet */
	if (!FILELAYOUT_LSEG(lseg)->commit_through_mds)
		data->args.stable = NFS_FILE_SYNC;

	data->write_done_cb = filelayout_write_done_cb;
	data->ds_clp = ds->ds_clp;
	fh = nfs4_fl_select_ds_fh(lseg, j);
	if (fh)
		data->args.fh = fh;
	/*
	 * Get the file offset on the dserver. Set the write offset to
	 * this offset and save the original offset.
	 */
	data->args.offset = filelayout_get_dserver_offset(lseg, offset);
	data->mds_offset = offset;

	/* Perform an asynchronous write */
	status = nfs_initiate_write(data, ds->ds_clp->cl_rpcclient,
				    &filelayout_write_call_ops, sync);
	BUG_ON(status != 0);
	return PNFS_ATTEMPTED;
}

/*
 * filelayout_check_layout()
 *
 * Make sure layout segment parameters are sane WRT the device.
 * At this point no generic layer initialization of the lseg has occurred,
 * and nothing has been added to the layout_hdr cache.
 *
 */
static int
filelayout_check_layout(struct pnfs_layout_hdr *lo,
			struct nfs4_filelayout_segment *fl,
			struct nfs4_layoutget_res *lgr,
			struct nfs4_deviceid *id)
{
	struct nfs4_file_layout_dsaddr *dsaddr;
	int status = -EINVAL;
	struct nfs_server *nfss = NFS_SERVER(lo->plh_inode);

	dprintk("--> %s\n", __func__);

	if (fl->pattern_offset > lgr->range.offset) {
		dprintk("%s pattern_offset %lld to large\n",
				__func__, fl->pattern_offset);
		goto out;
	}

	if (!fl->stripe_unit || fl->stripe_unit % PAGE_SIZE) {
		dprintk("%s Invalid stripe unit (%u)\n",
			__func__, fl->stripe_unit);
		goto out;
	}

	/* find and reference the deviceid */
	dsaddr = nfs4_fl_find_get_deviceid(id);
	if (dsaddr == NULL) {
		dsaddr = get_device_info(lo->plh_inode, id);
		if (dsaddr == NULL)
			goto out;
	}
	fl->dsaddr = dsaddr;

	if (fl->first_stripe_index < 0 ||
	    fl->first_stripe_index >= dsaddr->stripe_count) {
		dprintk("%s Bad first_stripe_index %d\n",
				__func__, fl->first_stripe_index);
		goto out_put;
	}

	if ((fl->stripe_type == STRIPE_SPARSE &&
	    fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) ||
	    (fl->stripe_type == STRIPE_DENSE &&
	    fl->num_fh != dsaddr->stripe_count)) {
		dprintk("%s num_fh %u not valid for given packing\n",
			__func__, fl->num_fh);
		goto out_put;
	}

	if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) {
		dprintk("%s Stripe unit (%u) not aligned with rsize %u "
			"wsize %u\n", __func__, fl->stripe_unit, nfss->rsize,
			nfss->wsize);
	}

	status = 0;
out:
	dprintk("--> %s returns %d\n", __func__, status);
	return status;
out_put:
	nfs4_fl_put_deviceid(dsaddr);
	goto out;
}

static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl)
{
	int i;

	for (i = 0; i < fl->num_fh; i++) {
		if (!fl->fh_array[i])
			break;
		kfree(fl->fh_array[i]);
	}
	kfree(fl->fh_array);
	fl->fh_array = NULL;
}

static void
_filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
{
	filelayout_free_fh_array(fl);
	kfree(fl);
}

static int
filelayout_decode_layout(struct pnfs_layout_hdr *flo,
			 struct nfs4_filelayout_segment *fl,
			 struct nfs4_layoutget_res *lgr,
			 struct nfs4_deviceid *id)
{
	uint32_t *p = (uint32_t *)lgr->layout.buf;
	uint32_t nfl_util;
	int i;

	dprintk("%s: set_layout_map Begin\n", __func__);

	memcpy(id, p, sizeof(*id));
	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
	print_deviceid(id);

	nfl_util = be32_to_cpup(p++);
	if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
		fl->commit_through_mds = 1;
	if (nfl_util & NFL4_UFLG_DENSE)
		fl->stripe_type = STRIPE_DENSE;
	else
		fl->stripe_type = STRIPE_SPARSE;
	fl->stripe_unit = nfl_util & ~NFL4_UFLG_MASK;

	fl->first_stripe_index = be32_to_cpup(p++);
	p = xdr_decode_hyper(p, &fl->pattern_offset);
	fl->num_fh = be32_to_cpup(p++);

	dprintk("%s: nfl_util 0x%X num_fh %u fsi %u po %llu\n",
		__func__, nfl_util, fl->num_fh, fl->first_stripe_index,
		fl->pattern_offset);

	fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *),
			       GFP_KERNEL);
	if (!fl->fh_array)
		return -ENOMEM;

	for (i = 0; i < fl->num_fh; i++) {
		/* Do we want to use a mempool here? */
		fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL);
		if (!fl->fh_array[i]) {
			filelayout_free_fh_array(fl);
			return -ENOMEM;
		}
		fl->fh_array[i]->size = be32_to_cpup(p++);
		if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
			printk(KERN_ERR "Too big fh %d received %d\n",
			       i, fl->fh_array[i]->size);
			filelayout_free_fh_array(fl);
			return -EIO;
		}
		memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size);
		p += XDR_QUADLEN(fl->fh_array[i]->size);
		dprintk("DEBUG: %s: fh len %d\n", __func__,
			fl->fh_array[i]->size);
	}

	return 0;
}

static struct pnfs_layout_segment *
filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
		      struct nfs4_layoutget_res *lgr)
{
	struct nfs4_filelayout_segment *fl;
	int rc;
	struct nfs4_deviceid id;

	dprintk("--> %s\n", __func__);
	fl = kzalloc(sizeof(*fl), GFP_KERNEL);
	if (!fl)
		return NULL;

	rc = filelayout_decode_layout(layoutid, fl, lgr, &id);
	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id)) {
		_filelayout_free_lseg(fl);
		return NULL;
	}
	return &fl->generic_hdr;
}

static void
filelayout_free_lseg(struct pnfs_layout_segment *lseg)
{
	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);

	dprintk("--> %s\n", __func__);
	nfs4_fl_put_deviceid(fl->dsaddr);
	_filelayout_free_lseg(fl);
}

/*
 * filelayout_pg_test(). Called by nfs_can_coalesce_requests()
 *
 * return 1 :  coalesce page
 * return 0 :  don't coalesce page
 */
int
filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
		   struct nfs_page *req)
{
	u64 p_stripe, r_stripe;
	u32 stripe_unit;

	if (!pgio->pg_lseg)
		return 1;
	p_stripe = (u64)prev->wb_index << PAGE_CACHE_SHIFT;
	r_stripe = (u64)req->wb_index << PAGE_CACHE_SHIFT;
	stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;

	do_div(p_stripe, stripe_unit);
	do_div(r_stripe, stripe_unit);

	return (p_stripe == r_stripe);
}

static struct pnfs_layoutdriver_type filelayout_type = {
	.id			= LAYOUT_NFSV4_1_FILES,
	.name			= "LAYOUT_NFSV4_1_FILES",
	.owner			= THIS_MODULE,
	.alloc_lseg		= filelayout_alloc_lseg,
	.free_lseg		= filelayout_free_lseg,
	.pg_test		= filelayout_pg_test,
	.read_pagelist		= filelayout_read_pagelist,
	.write_pagelist		= filelayout_write_pagelist,
};

static int __init nfs4filelayout_init(void)
{
	printk(KERN_INFO "%s: NFSv4 File Layout Driver Registering...\n",
	       __func__);
	return pnfs_register_layoutdriver(&filelayout_type);
}

static void __exit nfs4filelayout_exit(void)
{
	printk(KERN_INFO "%s: NFSv4 File Layout Driver Unregistering...\n",
	       __func__);
	pnfs_unregister_layoutdriver(&filelayout_type);
}

module_init(nfs4filelayout_init);
module_exit(nfs4filelayout_exit);