summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_log_cil.c
blob: 53abd6b0a3334ff50cea7262414a04a5f4d4f546 (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
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
/*
 * Copyright (c) 2010 Red Hat, Inc. All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */

#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log_priv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_error.h"
#include "xfs_alloc.h"

/*
 * Perform initial CIL structure initialisation. If the CIL is not
 * enabled in this filesystem, ensure the log->l_cilp is null so
 * we can check this conditional to determine if we are doing delayed
 * logging or not.
 */
int
xlog_cil_init(
	struct log	*log)
{
	struct xfs_cil	*cil;
	struct xfs_cil_ctx *ctx;

	log->l_cilp = NULL;
	if (!(log->l_mp->m_flags & XFS_MOUNT_DELAYLOG))
		return 0;

	cil = kmem_zalloc(sizeof(*cil), KM_SLEEP|KM_MAYFAIL);
	if (!cil)
		return ENOMEM;

	ctx = kmem_zalloc(sizeof(*ctx), KM_SLEEP|KM_MAYFAIL);
	if (!ctx) {
		kmem_free(cil);
		return ENOMEM;
	}

	INIT_LIST_HEAD(&cil->xc_cil);
	INIT_LIST_HEAD(&cil->xc_committing);
	spin_lock_init(&cil->xc_cil_lock);
	init_rwsem(&cil->xc_ctx_lock);
	sv_init(&cil->xc_commit_wait, SV_DEFAULT, "cilwait");

	INIT_LIST_HEAD(&ctx->committing);
	INIT_LIST_HEAD(&ctx->busy_extents);
	ctx->sequence = 1;
	ctx->cil = cil;
	cil->xc_ctx = ctx;

	cil->xc_log = log;
	log->l_cilp = cil;
	return 0;
}

void
xlog_cil_destroy(
	struct log	*log)
{
	if (!log->l_cilp)
		return;

	if (log->l_cilp->xc_ctx) {
		if (log->l_cilp->xc_ctx->ticket)
			xfs_log_ticket_put(log->l_cilp->xc_ctx->ticket);
		kmem_free(log->l_cilp->xc_ctx);
	}

	ASSERT(list_empty(&log->l_cilp->xc_cil));
	kmem_free(log->l_cilp);
}

/*
 * Allocate a new ticket. Failing to get a new ticket makes it really hard to
 * recover, so we don't allow failure here. Also, we allocate in a context that
 * we don't want to be issuing transactions from, so we need to tell the
 * allocation code this as well.
 *
 * We don't reserve any space for the ticket - we are going to steal whatever
 * space we require from transactions as they commit. To ensure we reserve all
 * the space required, we need to set the current reservation of the ticket to
 * zero so that we know to steal the initial transaction overhead from the
 * first transaction commit.
 */
static struct xlog_ticket *
xlog_cil_ticket_alloc(
	struct log	*log)
{
	struct xlog_ticket *tic;

	tic = xlog_ticket_alloc(log, 0, 1, XFS_TRANSACTION, 0,
				KM_SLEEP|KM_NOFS);
	tic->t_trans_type = XFS_TRANS_CHECKPOINT;

	/*
	 * set the current reservation to zero so we know to steal the basic
	 * transaction overhead reservation from the first transaction commit.
	 */
	tic->t_curr_res = 0;
	return tic;
}

/*
 * After the first stage of log recovery is done, we know where the head and
 * tail of the log are. We need this log initialisation done before we can
 * initialise the first CIL checkpoint context.
 *
 * Here we allocate a log ticket to track space usage during a CIL push.  This
 * ticket is passed to xlog_write() directly so that we don't slowly leak log
 * space by failing to account for space used by log headers and additional
 * region headers for split regions.
 */
void
xlog_cil_init_post_recovery(
	struct log	*log)
{
	if (!log->l_cilp)
		return;

	log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log);
	log->l_cilp->xc_ctx->sequence = 1;
	log->l_cilp->xc_ctx->commit_lsn = xlog_assign_lsn(log->l_curr_cycle,
								log->l_curr_block);
}

/*
 * Insert the log item into the CIL and calculate the difference in space
 * consumed by the item. Add the space to the checkpoint ticket and calculate
 * if the change requires additional log metadata. If it does, take that space
 * as well. Remove the amount of space we addded to the checkpoint ticket from
 * the current transaction ticket so that the accounting works out correctly.
 *
 * If this is the first time the item is being placed into the CIL in this
 * context, pin it so it can't be written to disk until the CIL is flushed to
 * the iclog and the iclog written to disk.
 */
static void
xlog_cil_insert(
	struct log		*log,
	struct xlog_ticket	*ticket,
	struct xfs_log_item	*item,
	struct xfs_log_vec	*lv)
{
	struct xfs_cil		*cil = log->l_cilp;
	struct xfs_log_vec	*old = lv->lv_item->li_lv;
	struct xfs_cil_ctx	*ctx = cil->xc_ctx;
	int			len;
	int			diff_iovecs;
	int			iclog_space;

	if (old) {
		/* existing lv on log item, space used is a delta */
		ASSERT(!list_empty(&item->li_cil));
		ASSERT(old->lv_buf && old->lv_buf_len && old->lv_niovecs);

		len = lv->lv_buf_len - old->lv_buf_len;
		diff_iovecs = lv->lv_niovecs - old->lv_niovecs;
		kmem_free(old->lv_buf);
		kmem_free(old);
	} else {
		/* new lv, must pin the log item */
		ASSERT(!lv->lv_item->li_lv);
		ASSERT(list_empty(&item->li_cil));

		len = lv->lv_buf_len;
		diff_iovecs = lv->lv_niovecs;
		IOP_PIN(lv->lv_item);

	}
	len += diff_iovecs * sizeof(xlog_op_header_t);

	/* attach new log vector to log item */
	lv->lv_item->li_lv = lv;

	spin_lock(&cil->xc_cil_lock);
	list_move_tail(&item->li_cil, &cil->xc_cil);
	ctx->nvecs += diff_iovecs;

	/*
	 * Now transfer enough transaction reservation to the context ticket
	 * for the checkpoint. The context ticket is special - the unit
	 * reservation has to grow as well as the current reservation as we
	 * steal from tickets so we can correctly determine the space used
	 * during the transaction commit.
	 */
	if (ctx->ticket->t_curr_res == 0) {
		/* first commit in checkpoint, steal the header reservation */
		ASSERT(ticket->t_curr_res >= ctx->ticket->t_unit_res + len);
		ctx->ticket->t_curr_res = ctx->ticket->t_unit_res;
		ticket->t_curr_res -= ctx->ticket->t_unit_res;
	}

	/* do we need space for more log record headers? */
	iclog_space = log->l_iclog_size - log->l_iclog_hsize;
	if (len > 0 && (ctx->space_used / iclog_space !=
				(ctx->space_used + len) / iclog_space)) {
		int hdrs;

		hdrs = (len + iclog_space - 1) / iclog_space;
		/* need to take into account split region headers, too */
		hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
		ctx->ticket->t_unit_res += hdrs;
		ctx->ticket->t_curr_res += hdrs;
		ticket->t_curr_res -= hdrs;
		ASSERT(ticket->t_curr_res >= len);
	}
	ticket->t_curr_res -= len;
	ctx->space_used += len;

	spin_unlock(&cil->xc_cil_lock);
}

/*
 * Format log item into a flat buffers
 *
 * For delayed logging, we need to hold a formatted buffer containing all the
 * changes on the log item. This enables us to relog the item in memory and
 * write it out asynchronously without needing to relock the object that was
 * modified at the time it gets written into the iclog.
 *
 * This function builds a vector for the changes in each log item in the
 * transaction. It then works out the length of the buffer needed for each log
 * item, allocates them and formats the vector for the item into the buffer.
 * The buffer is then attached to the log item are then inserted into the
 * Committed Item List for tracking until the next checkpoint is written out.
 *
 * We don't set up region headers during this process; we simply copy the
 * regions into the flat buffer. We can do this because we still have to do a
 * formatting step to write the regions into the iclog buffer.  Writing the
 * ophdrs during the iclog write means that we can support splitting large
 * regions across iclog boundares without needing a change in the format of the
 * item/region encapsulation.
 *
 * Hence what we need to do now is change the rewrite the vector array to point
 * to the copied region inside the buffer we just allocated. This allows us to
 * format the regions into the iclog as though they are being formatted
 * directly out of the objects themselves.
 */
static void
xlog_cil_format_items(
	struct log		*log,
	struct xfs_log_vec	*log_vector,
	struct xlog_ticket	*ticket,
	xfs_lsn_t		*start_lsn)
{
	struct xfs_log_vec *lv;

	if (start_lsn)
		*start_lsn = log->l_cilp->xc_ctx->sequence;

	ASSERT(log_vector);
	for (lv = log_vector; lv; lv = lv->lv_next) {
		void	*ptr;
		int	index;
		int	len = 0;

		/* build the vector array and calculate it's length */
		IOP_FORMAT(lv->lv_item, lv->lv_iovecp);
		for (index = 0; index < lv->lv_niovecs; index++)
			len += lv->lv_iovecp[index].i_len;

		lv->lv_buf_len = len;
		lv->lv_buf = kmem_zalloc(lv->lv_buf_len, KM_SLEEP|KM_NOFS);
		ptr = lv->lv_buf;

		for (index = 0; index < lv->lv_niovecs; index++) {
			struct xfs_log_iovec *vec = &lv->lv_iovecp[index];

			memcpy(ptr, vec->i_addr, vec->i_len);
			vec->i_addr = ptr;
			ptr += vec->i_len;
		}
		ASSERT(ptr == lv->lv_buf + lv->lv_buf_len);

		xlog_cil_insert(log, ticket, lv->lv_item, lv);
	}
}

static void
xlog_cil_free_logvec(
	struct xfs_log_vec	*log_vector)
{
	struct xfs_log_vec	*lv;

	for (lv = log_vector; lv; ) {
		struct xfs_log_vec *next = lv->lv_next;
		kmem_free(lv->lv_buf);
		kmem_free(lv);
		lv = next;
	}
}

/*
 * Commit a transaction with the given vector to the Committed Item List.
 *
 * To do this, we need to format the item, pin it in memory if required and
 * account for the space used by the transaction. Once we have done that we
 * need to release the unused reservation for the transaction, attach the
 * transaction to the checkpoint context so we carry the busy extents through
 * to checkpoint completion, and then unlock all the items in the transaction.
 *
 * For more specific information about the order of operations in
 * xfs_log_commit_cil() please refer to the comments in
 * xfs_trans_commit_iclog().
 */
int
xfs_log_commit_cil(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	struct xfs_log_vec	*log_vector,
	xfs_lsn_t		*commit_lsn,
	int			flags)
{
	struct log		*log = mp->m_log;
	int			log_flags = 0;

	if (flags & XFS_TRANS_RELEASE_LOG_RES)
		log_flags = XFS_LOG_REL_PERM_RESERV;

	if (XLOG_FORCED_SHUTDOWN(log)) {
		xlog_cil_free_logvec(log_vector);
		return XFS_ERROR(EIO);
	}

	/* lock out background commit */
	down_read(&log->l_cilp->xc_ctx_lock);
	xlog_cil_format_items(log, log_vector, tp->t_ticket, commit_lsn);

	/* check we didn't blow the reservation */
	if (tp->t_ticket->t_curr_res < 0)
		xlog_print_tic_res(log->l_mp, tp->t_ticket);

	/* attach the transaction to the CIL if it has any busy extents */
	if (!list_empty(&tp->t_busy)) {
		spin_lock(&log->l_cilp->xc_cil_lock);
		list_splice_init(&tp->t_busy,
					&log->l_cilp->xc_ctx->busy_extents);
		spin_unlock(&log->l_cilp->xc_cil_lock);
	}

	tp->t_commit_lsn = *commit_lsn;
	xfs_log_done(mp, tp->t_ticket, NULL, log_flags);
	xfs_trans_unreserve_and_mod_sb(tp);

	/* background commit is allowed again */
	up_read(&log->l_cilp->xc_ctx_lock);
	return 0;
}

/*
 * Mark all items committed and clear busy extents. We free the log vector
 * chains in a separate pass so that we unpin the log items as quickly as
 * possible.
 */
static void
xlog_cil_committed(
	void	*args,
	int	abort)
{
	struct xfs_cil_ctx	*ctx = args;
	struct xfs_log_vec	*lv;
	int			abortflag = abort ? XFS_LI_ABORTED : 0;
	struct xfs_busy_extent	*busyp, *n;

	/* unpin all the log items */
	for (lv = ctx->lv_chain; lv; lv = lv->lv_next ) {
		xfs_trans_item_committed(lv->lv_item, ctx->start_lsn,
							abortflag);
	}

	list_for_each_entry_safe(busyp, n, &ctx->busy_extents, list)
		xfs_alloc_busy_clear(ctx->cil->xc_log->l_mp, busyp);

	spin_lock(&ctx->cil->xc_cil_lock);
	list_del(&ctx->committing);
	spin_unlock(&ctx->cil->xc_cil_lock);

	xlog_cil_free_logvec(ctx->lv_chain);
	kmem_free(ctx);
}

/*
 * Push the Committed Item List to the log. If the push_now flag is not set,
 * then it is a background flush and so we can chose to ignore it.
 */
int
xlog_cil_push(
	struct log		*log,
	int			push_now)
{
	struct xfs_cil		*cil = log->l_cilp;
	struct xfs_log_vec	*lv;
	struct xfs_cil_ctx	*ctx;
	struct xfs_cil_ctx	*new_ctx;
	struct xlog_in_core	*commit_iclog;
	struct xlog_ticket	*tic;
	int			num_lv;
	int			num_iovecs;
	int			len;
	int			error = 0;
	struct xfs_trans_header thdr;
	struct xfs_log_iovec	lhdr;
	struct xfs_log_vec	lvhdr = { NULL };
	xfs_lsn_t		commit_lsn;

	if (!cil)
		return 0;

	/* XXX: don't sleep for background? */
	new_ctx = kmem_zalloc(sizeof(*new_ctx), KM_SLEEP|KM_NOFS);
	new_ctx->ticket = xlog_cil_ticket_alloc(log);

	/* lock out transaction commit */
	down_write(&cil->xc_ctx_lock);
	ctx = cil->xc_ctx;

	/* check if we've anything to push */
	if (list_empty(&cil->xc_cil))
		goto out_skip;

	/*
	 * pull all the log vectors off the items in the CIL, and
	 * remove the items from the CIL. We don't need the CIL lock
	 * here because it's only needed on the transaction commit
	 * side which is currently locked out by the flush lock.
	 */
	lv = NULL;
	num_lv = 0;
	num_iovecs = 0;
	len = 0;
	while (!list_empty(&cil->xc_cil)) {
		struct xfs_log_item	*item;
		int			i;

		item = list_first_entry(&cil->xc_cil,
					struct xfs_log_item, li_cil);
		list_del_init(&item->li_cil);
		if (!ctx->lv_chain)
			ctx->lv_chain = item->li_lv;
		else
			lv->lv_next = item->li_lv;
		lv = item->li_lv;
		item->li_lv = NULL;

		num_lv++;
		num_iovecs += lv->lv_niovecs;
		for (i = 0; i < lv->lv_niovecs; i++)
			len += lv->lv_iovecp[i].i_len;
	}

	/*
	 * initialise the new context and attach it to the CIL. Then attach
	 * the current context to the CIL committing lsit so it can be found
	 * during log forces to extract the commit lsn of the sequence that
	 * needs to be forced.
	 */
	INIT_LIST_HEAD(&new_ctx->committing);
	INIT_LIST_HEAD(&new_ctx->busy_extents);
	new_ctx->sequence = ctx->sequence + 1;
	new_ctx->cil = cil;
	cil->xc_ctx = new_ctx;

	/*
	 * The switch is now done, so we can drop the context lock and move out
	 * of a shared context. We can't just go straight to the commit record,
	 * though - we need to synchronise with previous and future commits so
	 * that the commit records are correctly ordered in the log to ensure
	 * that we process items during log IO completion in the correct order.
	 *
	 * For example, if we get an EFI in one checkpoint and the EFD in the
	 * next (e.g. due to log forces), we do not want the checkpoint with
	 * the EFD to be committed before the checkpoint with the EFI.  Hence
	 * we must strictly order the commit records of the checkpoints so
	 * that: a) the checkpoint callbacks are attached to the iclogs in the
	 * correct order; and b) the checkpoints are replayed in correct order
	 * in log recovery.
	 *
	 * Hence we need to add this context to the committing context list so
	 * that higher sequences will wait for us to write out a commit record
	 * before they do.
	 */
	spin_lock(&cil->xc_cil_lock);
	list_add(&ctx->committing, &cil->xc_committing);
	spin_unlock(&cil->xc_cil_lock);
	up_write(&cil->xc_ctx_lock);

	/*
	 * Build a checkpoint transaction header and write it to the log to
	 * begin the transaction. We need to account for the space used by the
	 * transaction header here as it is not accounted for in xlog_write().
	 *
	 * The LSN we need to pass to the log items on transaction commit is
	 * the LSN reported by the first log vector write. If we use the commit
	 * record lsn then we can move the tail beyond the grant write head.
	 */
	tic = ctx->ticket;
	thdr.th_magic = XFS_TRANS_HEADER_MAGIC;
	thdr.th_type = XFS_TRANS_CHECKPOINT;
	thdr.th_tid = tic->t_tid;
	thdr.th_num_items = num_iovecs;
	lhdr.i_addr = (xfs_caddr_t)&thdr;
	lhdr.i_len = sizeof(xfs_trans_header_t);
	lhdr.i_type = XLOG_REG_TYPE_TRANSHDR;
	tic->t_curr_res -= lhdr.i_len + sizeof(xlog_op_header_t);

	lvhdr.lv_niovecs = 1;
	lvhdr.lv_iovecp = &lhdr;
	lvhdr.lv_next = ctx->lv_chain;

	error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0);
	if (error)
		goto out_abort;

	/*
	 * now that we've written the checkpoint into the log, strictly
	 * order the commit records so replay will get them in the right order.
	 */
restart:
	spin_lock(&cil->xc_cil_lock);
	list_for_each_entry(new_ctx, &cil->xc_committing, committing) {
		/*
		 * Higher sequences will wait for this one so skip them.
		 * Don't wait for own own sequence, either.
		 */
		if (new_ctx->sequence >= ctx->sequence)
			continue;
		if (!new_ctx->commit_lsn) {
			/*
			 * It is still being pushed! Wait for the push to
			 * complete, then start again from the beginning.
			 */
			sv_wait(&cil->xc_commit_wait, 0, &cil->xc_cil_lock, 0);
			goto restart;
		}
	}
	spin_unlock(&cil->xc_cil_lock);

	commit_lsn = xfs_log_done(log->l_mp, tic, &commit_iclog, 0);
	if (error || commit_lsn == -1)
		goto out_abort;

	/* attach all the transactions w/ busy extents to iclog */
	ctx->log_cb.cb_func = xlog_cil_committed;
	ctx->log_cb.cb_arg = ctx;
	error = xfs_log_notify(log->l_mp, commit_iclog, &ctx->log_cb);
	if (error)
		goto out_abort;

	/*
	 * now the checkpoint commit is complete and we've attached the
	 * callbacks to the iclog we can assign the commit LSN to the context
	 * and wake up anyone who is waiting for the commit to complete.
	 */
	spin_lock(&cil->xc_cil_lock);
	ctx->commit_lsn = commit_lsn;
	sv_broadcast(&cil->xc_commit_wait);
	spin_unlock(&cil->xc_cil_lock);

	/* release the hounds! */
	return xfs_log_release_iclog(log->l_mp, commit_iclog);

out_skip:
	up_write(&cil->xc_ctx_lock);
	xfs_log_ticket_put(new_ctx->ticket);
	kmem_free(new_ctx);
	return 0;

out_abort:
	xlog_cil_committed(ctx, XFS_LI_ABORTED);
	return XFS_ERROR(EIO);
}

/*
 * Conditionally push the CIL based on the sequence passed in.
 *
 * We only need to push if we haven't already pushed the sequence
 * number given. Hence the only time we will trigger a push here is
 * if the push sequence is the same as the current context.
 *
 * We return the current commit lsn to allow the callers to determine if a
 * iclog flush is necessary following this call.
 *
 * XXX: Initially, just push the CIL unconditionally and return whatever
 * commit lsn is there. It'll be empty, so this is broken for now.
 */
xfs_lsn_t
xlog_cil_push_lsn(
	struct log	*log,
	xfs_lsn_t	push_seq)
{
	struct xfs_cil		*cil = log->l_cilp;
	struct xfs_cil_ctx	*ctx;
	xfs_lsn_t		commit_lsn = NULLCOMMITLSN;

restart:
	down_write(&cil->xc_ctx_lock);
	ASSERT(push_seq <= cil->xc_ctx->sequence);

	/* check to see if we need to force out the current context */
	if (push_seq == cil->xc_ctx->sequence) {
		up_write(&cil->xc_ctx_lock);
		xlog_cil_push(log, 1);
		goto restart;
	}

	/*
	 * See if we can find a previous sequence still committing.
	 * We can drop the flush lock as soon as we have the cil lock
	 * because we are now only comparing contexts protected by
	 * the cil lock.
	 *
	 * We need to wait for all previous sequence commits to complete
	 * before allowing the force of push_seq to go ahead. Hence block
	 * on commits for those as well.
	 */
	spin_lock(&cil->xc_cil_lock);
	up_write(&cil->xc_ctx_lock);
	list_for_each_entry(ctx, &cil->xc_committing, committing) {
		if (ctx->sequence > push_seq)
			continue;
		if (!ctx->commit_lsn) {
			/*
			 * It is still being pushed! Wait for the push to
			 * complete, then start again from the beginning.
			 */
			sv_wait(&cil->xc_commit_wait, 0, &cil->xc_cil_lock, 0);
			goto restart;
		}
		if (ctx->sequence != push_seq)
			continue;
		/* found it! */
		commit_lsn = ctx->commit_lsn;
	}
	spin_unlock(&cil->xc_cil_lock);
	return commit_lsn;
}