xref: /kernel/linux/linux-5.10/fs/gfs2/glops.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
4 * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
5 */
6
7#include <linux/spinlock.h>
8#include <linux/completion.h>
9#include <linux/buffer_head.h>
10#include <linux/gfs2_ondisk.h>
11#include <linux/bio.h>
12#include <linux/posix_acl.h>
13#include <linux/security.h>
14
15#include "gfs2.h"
16#include "incore.h"
17#include "bmap.h"
18#include "glock.h"
19#include "glops.h"
20#include "inode.h"
21#include "log.h"
22#include "meta_io.h"
23#include "recovery.h"
24#include "rgrp.h"
25#include "util.h"
26#include "trans.h"
27#include "dir.h"
28#include "lops.h"
29
30struct workqueue_struct *gfs2_freeze_wq;
31
32extern struct workqueue_struct *gfs2_control_wq;
33
34static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
35{
36	fs_err(gl->gl_name.ln_sbd,
37	       "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page "
38	       "state 0x%lx\n",
39	       bh, (unsigned long long)bh->b_blocknr, bh->b_state,
40	       bh->b_page->mapping, bh->b_page->flags);
41	fs_err(gl->gl_name.ln_sbd, "AIL glock %u:%llu mapping %p\n",
42	       gl->gl_name.ln_type, gl->gl_name.ln_number,
43	       gfs2_glock2aspace(gl));
44	gfs2_lm(gl->gl_name.ln_sbd, "AIL error\n");
45	gfs2_withdraw(gl->gl_name.ln_sbd);
46}
47
48/**
49 * __gfs2_ail_flush - remove all buffers for a given lock from the AIL
50 * @gl: the glock
51 * @fsync: set when called from fsync (not all buffers will be clean)
52 *
53 * None of the buffers should be dirty, locked, or pinned.
54 */
55
56static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync,
57			     unsigned int nr_revokes)
58{
59	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
60	struct list_head *head = &gl->gl_ail_list;
61	struct gfs2_bufdata *bd, *tmp;
62	struct buffer_head *bh;
63	const unsigned long b_state = (1UL << BH_Dirty)|(1UL << BH_Pinned)|(1UL << BH_Lock);
64
65	gfs2_log_lock(sdp);
66	spin_lock(&sdp->sd_ail_lock);
67	list_for_each_entry_safe_reverse(bd, tmp, head, bd_ail_gl_list) {
68		if (nr_revokes == 0)
69			break;
70		bh = bd->bd_bh;
71		if (bh->b_state & b_state) {
72			if (fsync)
73				continue;
74			gfs2_ail_error(gl, bh);
75		}
76		gfs2_trans_add_revoke(sdp, bd);
77		nr_revokes--;
78	}
79	GLOCK_BUG_ON(gl, !fsync && atomic_read(&gl->gl_ail_count));
80	spin_unlock(&sdp->sd_ail_lock);
81	gfs2_log_unlock(sdp);
82}
83
84
85static int gfs2_ail_empty_gl(struct gfs2_glock *gl)
86{
87	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
88	struct gfs2_trans tr;
89	int ret;
90
91	memset(&tr, 0, sizeof(tr));
92	INIT_LIST_HEAD(&tr.tr_buf);
93	INIT_LIST_HEAD(&tr.tr_databuf);
94	INIT_LIST_HEAD(&tr.tr_ail1_list);
95	INIT_LIST_HEAD(&tr.tr_ail2_list);
96	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
97
98	if (!tr.tr_revokes) {
99		bool have_revokes;
100		bool log_in_flight;
101
102		/*
103		 * We have nothing on the ail, but there could be revokes on
104		 * the sdp revoke queue, in which case, we still want to flush
105		 * the log and wait for it to finish.
106		 *
107		 * If the sdp revoke list is empty too, we might still have an
108		 * io outstanding for writing revokes, so we should wait for
109		 * it before returning.
110		 *
111		 * If none of these conditions are true, our revokes are all
112		 * flushed and we can return.
113		 */
114		gfs2_log_lock(sdp);
115		have_revokes = !list_empty(&sdp->sd_log_revokes);
116		log_in_flight = atomic_read(&sdp->sd_log_in_flight);
117		gfs2_log_unlock(sdp);
118		if (have_revokes)
119			goto flush;
120		if (log_in_flight)
121			log_flush_wait(sdp);
122		return 0;
123	}
124
125	/* A shortened, inline version of gfs2_trans_begin()
126         * tr->alloced is not set since the transaction structure is
127         * on the stack */
128	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes);
129	tr.tr_ip = _RET_IP_;
130	ret = gfs2_log_reserve(sdp, tr.tr_reserved);
131	if (ret < 0)
132		return ret;
133	WARN_ON_ONCE(current->journal_info);
134	current->journal_info = &tr;
135
136	__gfs2_ail_flush(gl, 0, tr.tr_revokes);
137
138	gfs2_trans_end(sdp);
139flush:
140	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
141		       GFS2_LFC_AIL_EMPTY_GL);
142	return 0;
143}
144
145void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
146{
147	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
148	unsigned int revokes = atomic_read(&gl->gl_ail_count);
149	unsigned int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
150	int ret;
151
152	if (!revokes)
153		return;
154
155	while (revokes > max_revokes)
156		max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
157
158	ret = gfs2_trans_begin(sdp, 0, max_revokes);
159	if (ret)
160		return;
161	__gfs2_ail_flush(gl, fsync, max_revokes);
162	gfs2_trans_end(sdp);
163	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
164		       GFS2_LFC_AIL_FLUSH);
165}
166
167/**
168 * gfs2_rgrp_metasync - sync out the metadata of a resource group
169 * @gl: the glock protecting the resource group
170 *
171 */
172
173static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
174{
175	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
176	struct address_space *metamapping = &sdp->sd_aspace;
177	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
178	const unsigned bsize = sdp->sd_sb.sb_bsize;
179	loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
180	loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
181	int error;
182
183	filemap_fdatawrite_range(metamapping, start, end);
184	error = filemap_fdatawait_range(metamapping, start, end);
185	WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
186	mapping_set_error(metamapping, error);
187	if (error)
188		gfs2_io_error(sdp);
189	return error;
190}
191
192/**
193 * rgrp_go_sync - sync out the metadata for this glock
194 * @gl: the glock
195 *
196 * Called when demoting or unlocking an EX glock.  We must flush
197 * to disk all dirty buffers/pages relating to this glock, and must not
198 * return to caller to demote/unlock the glock until I/O is complete.
199 */
200
201static int rgrp_go_sync(struct gfs2_glock *gl)
202{
203	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
204	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
205	int error;
206
207	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
208		return 0;
209	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
210
211	gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
212		       GFS2_LFC_RGRP_GO_SYNC);
213	error = gfs2_rgrp_metasync(gl);
214	if (!error)
215		error = gfs2_ail_empty_gl(gl);
216	gfs2_free_clones(rgd);
217	return error;
218}
219
220/**
221 * rgrp_go_inval - invalidate the metadata for this glock
222 * @gl: the glock
223 * @flags:
224 *
225 * We never used LM_ST_DEFERRED with resource groups, so that we
226 * should always see the metadata flag set here.
227 *
228 */
229
230static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
231{
232	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
233	struct address_space *mapping = &sdp->sd_aspace;
234	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
235	const unsigned bsize = sdp->sd_sb.sb_bsize;
236	loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
237	loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
238
239	gfs2_rgrp_brelse(rgd);
240	WARN_ON_ONCE(!(flags & DIO_METADATA));
241	truncate_inode_pages_range(mapping, start, end);
242	rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
243}
244
245static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
246			      const char *fs_id_buf)
247{
248	struct gfs2_rgrpd *rgd = gl->gl_object;
249
250	if (rgd)
251		gfs2_rgrp_dump(seq, rgd, fs_id_buf);
252}
253
254static struct gfs2_inode *gfs2_glock2inode(struct gfs2_glock *gl)
255{
256	struct gfs2_inode *ip;
257
258	spin_lock(&gl->gl_lockref.lock);
259	ip = gl->gl_object;
260	if (ip)
261		set_bit(GIF_GLOP_PENDING, &ip->i_flags);
262	spin_unlock(&gl->gl_lockref.lock);
263	return ip;
264}
265
266struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl)
267{
268	struct gfs2_rgrpd *rgd;
269
270	spin_lock(&gl->gl_lockref.lock);
271	rgd = gl->gl_object;
272	spin_unlock(&gl->gl_lockref.lock);
273
274	return rgd;
275}
276
277static void gfs2_clear_glop_pending(struct gfs2_inode *ip)
278{
279	if (!ip)
280		return;
281
282	clear_bit_unlock(GIF_GLOP_PENDING, &ip->i_flags);
283	wake_up_bit(&ip->i_flags, GIF_GLOP_PENDING);
284}
285
286/**
287 * gfs2_inode_metasync - sync out the metadata of an inode
288 * @gl: the glock protecting the inode
289 *
290 */
291int gfs2_inode_metasync(struct gfs2_glock *gl)
292{
293	struct address_space *metamapping = gfs2_glock2aspace(gl);
294	int error;
295
296	filemap_fdatawrite(metamapping);
297	error = filemap_fdatawait(metamapping);
298	if (error)
299		gfs2_io_error(gl->gl_name.ln_sbd);
300	return error;
301}
302
303/**
304 * inode_go_sync - Sync the dirty metadata of an inode
305 * @gl: the glock protecting the inode
306 *
307 */
308
309static int inode_go_sync(struct gfs2_glock *gl)
310{
311	struct gfs2_inode *ip = gfs2_glock2inode(gl);
312	int isreg = ip && S_ISREG(ip->i_inode.i_mode);
313	struct address_space *metamapping = gfs2_glock2aspace(gl);
314	int error = 0, ret;
315
316	if (isreg) {
317		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
318			unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
319		inode_dio_wait(&ip->i_inode);
320	}
321	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
322		goto out;
323
324	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
325
326	gfs2_log_flush(gl->gl_name.ln_sbd, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
327		       GFS2_LFC_INODE_GO_SYNC);
328	filemap_fdatawrite(metamapping);
329	if (isreg) {
330		struct address_space *mapping = ip->i_inode.i_mapping;
331		filemap_fdatawrite(mapping);
332		error = filemap_fdatawait(mapping);
333		mapping_set_error(mapping, error);
334	}
335	ret = gfs2_inode_metasync(gl);
336	if (!error)
337		error = ret;
338	gfs2_ail_empty_gl(gl);
339	/*
340	 * Writeback of the data mapping may cause the dirty flag to be set
341	 * so we have to clear it again here.
342	 */
343	smp_mb__before_atomic();
344	clear_bit(GLF_DIRTY, &gl->gl_flags);
345
346out:
347	gfs2_clear_glop_pending(ip);
348	return error;
349}
350
351/**
352 * inode_go_inval - prepare a inode glock to be released
353 * @gl: the glock
354 * @flags:
355 *
356 * Normally we invalidate everything, but if we are moving into
357 * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we
358 * can keep hold of the metadata, since it won't have changed.
359 *
360 */
361
362static void inode_go_inval(struct gfs2_glock *gl, int flags)
363{
364	struct gfs2_inode *ip = gfs2_glock2inode(gl);
365
366	if (flags & DIO_METADATA) {
367		struct address_space *mapping = gfs2_glock2aspace(gl);
368		truncate_inode_pages(mapping, 0);
369		if (ip) {
370			set_bit(GIF_INVALID, &ip->i_flags);
371			forget_all_cached_acls(&ip->i_inode);
372			security_inode_invalidate_secctx(&ip->i_inode);
373			gfs2_dir_hash_inval(ip);
374		}
375	}
376
377	if (ip == GFS2_I(gl->gl_name.ln_sbd->sd_rindex)) {
378		gfs2_log_flush(gl->gl_name.ln_sbd, NULL,
379			       GFS2_LOG_HEAD_FLUSH_NORMAL |
380			       GFS2_LFC_INODE_GO_INVAL);
381		gl->gl_name.ln_sbd->sd_rindex_uptodate = 0;
382	}
383	if (ip && S_ISREG(ip->i_inode.i_mode))
384		truncate_inode_pages(ip->i_inode.i_mapping, 0);
385
386	gfs2_clear_glop_pending(ip);
387}
388
389/**
390 * inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
391 * @gl: the glock
392 *
393 * Returns: 1 if it's ok
394 */
395
396static int inode_go_demote_ok(const struct gfs2_glock *gl)
397{
398	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
399
400	if (sdp->sd_jindex == gl->gl_object || sdp->sd_rindex == gl->gl_object)
401		return 0;
402
403	return 1;
404}
405
406static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
407{
408	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
409	const struct gfs2_dinode *str = buf;
410	struct timespec64 atime;
411	u16 height, depth;
412
413	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
414		goto corrupt;
415	ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
416	ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
417	ip->i_inode.i_rdev = 0;
418	switch (ip->i_inode.i_mode & S_IFMT) {
419	case S_IFBLK:
420	case S_IFCHR:
421		ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
422					   be32_to_cpu(str->di_minor));
423		break;
424	}
425
426	i_uid_write(&ip->i_inode, be32_to_cpu(str->di_uid));
427	i_gid_write(&ip->i_inode, be32_to_cpu(str->di_gid));
428	set_nlink(&ip->i_inode, be32_to_cpu(str->di_nlink));
429	i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
430	gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
431	atime.tv_sec = be64_to_cpu(str->di_atime);
432	atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
433	if (timespec64_compare(&ip->i_inode.i_atime, &atime) < 0)
434		ip->i_inode.i_atime = atime;
435	ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
436	ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
437	ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
438	ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);
439
440	ip->i_goal = be64_to_cpu(str->di_goal_meta);
441	ip->i_generation = be64_to_cpu(str->di_generation);
442
443	ip->i_diskflags = be32_to_cpu(str->di_flags);
444	ip->i_eattr = be64_to_cpu(str->di_eattr);
445	/* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */
446	gfs2_set_inode_flags(&ip->i_inode);
447	height = be16_to_cpu(str->di_height);
448	if (unlikely(height > sdp->sd_max_height))
449		goto corrupt;
450	ip->i_height = (u8)height;
451
452	depth = be16_to_cpu(str->di_depth);
453	if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
454		goto corrupt;
455	ip->i_depth = (u8)depth;
456	ip->i_entries = be32_to_cpu(str->di_entries);
457
458	if (gfs2_is_stuffed(ip) && ip->i_inode.i_size > gfs2_max_stuffed_size(ip))
459		goto corrupt;
460
461	if (S_ISREG(ip->i_inode.i_mode))
462		gfs2_set_aops(&ip->i_inode);
463
464	return 0;
465corrupt:
466	gfs2_consist_inode(ip);
467	return -EIO;
468}
469
470/**
471 * gfs2_inode_refresh - Refresh the incore copy of the dinode
472 * @ip: The GFS2 inode
473 *
474 * Returns: errno
475 */
476
477int gfs2_inode_refresh(struct gfs2_inode *ip)
478{
479	struct buffer_head *dibh;
480	int error;
481
482	error = gfs2_meta_inode_buffer(ip, &dibh);
483	if (error)
484		return error;
485
486	error = gfs2_dinode_in(ip, dibh->b_data);
487	brelse(dibh);
488	clear_bit(GIF_INVALID, &ip->i_flags);
489
490	return error;
491}
492
493/**
494 * inode_go_lock - operation done after an inode lock is locked by a process
495 * @gl: the glock
496 * @flags:
497 *
498 * Returns: errno
499 */
500
501static int inode_go_lock(struct gfs2_holder *gh)
502{
503	struct gfs2_glock *gl = gh->gh_gl;
504	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
505	struct gfs2_inode *ip = gl->gl_object;
506	int error = 0;
507
508	if (!ip || (gh->gh_flags & GL_SKIP))
509		return 0;
510
511	if (test_bit(GIF_INVALID, &ip->i_flags)) {
512		error = gfs2_inode_refresh(ip);
513		if (error)
514			return error;
515	}
516
517	if (gh->gh_state != LM_ST_DEFERRED)
518		inode_dio_wait(&ip->i_inode);
519
520	if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) &&
521	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
522	    (gh->gh_state == LM_ST_EXCLUSIVE)) {
523		spin_lock(&sdp->sd_trunc_lock);
524		if (list_empty(&ip->i_trunc_list))
525			list_add(&ip->i_trunc_list, &sdp->sd_trunc_list);
526		spin_unlock(&sdp->sd_trunc_lock);
527		wake_up(&sdp->sd_quota_wait);
528		return 1;
529	}
530
531	return error;
532}
533
534/**
535 * inode_go_dump - print information about an inode
536 * @seq: The iterator
537 * @ip: the inode
538 * @fs_id_buf: file system id (may be empty)
539 *
540 */
541
542static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
543			  const char *fs_id_buf)
544{
545	struct gfs2_inode *ip = gl->gl_object;
546	struct inode *inode = &ip->i_inode;
547	unsigned long nrpages;
548
549	if (ip == NULL)
550		return;
551
552	xa_lock_irq(&inode->i_data.i_pages);
553	nrpages = inode->i_data.nrpages;
554	xa_unlock_irq(&inode->i_data.i_pages);
555
556	gfs2_print_dbg(seq, "%s I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu "
557		       "p:%lu\n", fs_id_buf,
558		  (unsigned long long)ip->i_no_formal_ino,
559		  (unsigned long long)ip->i_no_addr,
560		  IF2DT(ip->i_inode.i_mode), ip->i_flags,
561		  (unsigned int)ip->i_diskflags,
562		  (unsigned long long)i_size_read(inode), nrpages);
563}
564
565/**
566 * freeze_go_sync - promote/demote the freeze glock
567 * @gl: the glock
568 * @state: the requested state
569 * @flags:
570 *
571 */
572
573static int freeze_go_sync(struct gfs2_glock *gl)
574{
575	int error = 0;
576	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
577
578	/*
579	 * We need to check gl_state == LM_ST_SHARED here and not gl_req ==
580	 * LM_ST_EXCLUSIVE. That's because when any node does a freeze,
581	 * all the nodes should have the freeze glock in SH mode and they all
582	 * call do_xmote: One for EX and the others for UN. They ALL must
583	 * freeze locally, and they ALL must queue freeze work. The freeze_work
584	 * calls freeze_func, which tries to reacquire the freeze glock in SH,
585	 * effectively waiting for the thaw on the node who holds it in EX.
586	 * Once thawed, the work func acquires the freeze glock in
587	 * SH and everybody goes back to thawed.
588	 */
589	if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) &&
590	    !test_bit(SDF_NORECOVERY, &sdp->sd_flags)) {
591		atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
592		error = freeze_super(sdp->sd_vfs);
593		if (error) {
594			fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n",
595				error);
596			if (gfs2_withdrawn(sdp)) {
597				atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN);
598				return 0;
599			}
600			gfs2_assert_withdraw(sdp, 0);
601		}
602		queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work);
603		if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
604			gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
605				       GFS2_LFC_FREEZE_GO_SYNC);
606		else /* read-only mounts */
607			atomic_set(&sdp->sd_freeze_state, SFS_FROZEN);
608	}
609	return 0;
610}
611
612/**
613 * freeze_go_xmote_bh - After promoting/demoting the freeze glock
614 * @gl: the glock
615 *
616 */
617
618static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
619{
620	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
621	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
622	struct gfs2_glock *j_gl = ip->i_gl;
623	struct gfs2_log_header_host head;
624	int error;
625
626	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
627		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
628
629		error = gfs2_find_jhead(sdp->sd_jdesc, &head, false);
630		if (gfs2_assert_withdraw_delayed(sdp, !error))
631			return error;
632		if (gfs2_assert_withdraw_delayed(sdp, head.lh_flags &
633						 GFS2_LOG_HEAD_UNMOUNT))
634			return -EIO;
635		sdp->sd_log_sequence = head.lh_sequence + 1;
636		gfs2_log_pointers_init(sdp, head.lh_blkno);
637	}
638	return 0;
639}
640
641/**
642 * trans_go_demote_ok
643 * @gl: the glock
644 *
645 * Always returns 0
646 */
647
648static int freeze_go_demote_ok(const struct gfs2_glock *gl)
649{
650	return 0;
651}
652
653/**
654 * iopen_go_callback - schedule the dcache entry for the inode to be deleted
655 * @gl: the glock
656 *
657 * gl_lockref.lock lock is held while calling this
658 */
659static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
660{
661	struct gfs2_inode *ip = gl->gl_object;
662	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
663
664	if (!remote || sb_rdonly(sdp->sd_vfs))
665		return;
666
667	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
668	    gl->gl_state == LM_ST_SHARED && ip) {
669		gl->gl_lockref.count++;
670		if (!queue_delayed_work(gfs2_delete_workqueue,
671					&gl->gl_delete, 0))
672			gl->gl_lockref.count--;
673	}
674}
675
676static int iopen_go_demote_ok(const struct gfs2_glock *gl)
677{
678       return !gfs2_delete_work_queued(gl);
679}
680
681/**
682 * inode_go_free - wake up anyone waiting for dlm's unlock ast to free it
683 * @gl: glock being freed
684 *
685 * For now, this is only used for the journal inode glock. In withdraw
686 * situations, we need to wait for the glock to be freed so that we know
687 * other nodes may proceed with recovery / journal replay.
688 */
689static void inode_go_free(struct gfs2_glock *gl)
690{
691	/* Note that we cannot reference gl_object because it's already set
692	 * to NULL by this point in its lifecycle. */
693	if (!test_bit(GLF_FREEING, &gl->gl_flags))
694		return;
695	clear_bit_unlock(GLF_FREEING, &gl->gl_flags);
696	wake_up_bit(&gl->gl_flags, GLF_FREEING);
697}
698
699/**
700 * nondisk_go_callback - used to signal when a node did a withdraw
701 * @gl: the nondisk glock
702 * @remote: true if this came from a different cluster node
703 *
704 */
705static void nondisk_go_callback(struct gfs2_glock *gl, bool remote)
706{
707	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
708
709	/* Ignore the callback unless it's from another node, and it's the
710	   live lock. */
711	if (!remote || gl->gl_name.ln_number != GFS2_LIVE_LOCK)
712		return;
713
714	/* First order of business is to cancel the demote request. We don't
715	 * really want to demote a nondisk glock. At best it's just to inform
716	 * us of another node's withdraw. We'll keep it in SH mode. */
717	clear_bit(GLF_DEMOTE, &gl->gl_flags);
718	clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
719
720	/* Ignore the unlock if we're withdrawn, unmounting, or in recovery. */
721	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) ||
722	    test_bit(SDF_WITHDRAWN, &sdp->sd_flags) ||
723	    test_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags))
724		return;
725
726	/* We only care when a node wants us to unlock, because that means
727	 * they want a journal recovered. */
728	if (gl->gl_demote_state != LM_ST_UNLOCKED)
729		return;
730
731	if (sdp->sd_args.ar_spectator) {
732		fs_warn(sdp, "Spectator node cannot recover journals.\n");
733		return;
734	}
735
736	fs_warn(sdp, "Some node has withdrawn; checking for recovery.\n");
737	set_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags);
738	/*
739	 * We can't call remote_withdraw directly here or gfs2_recover_journal
740	 * because this is called from the glock unlock function and the
741	 * remote_withdraw needs to enqueue and dequeue the same "live" glock
742	 * we were called from. So we queue it to the control work queue in
743	 * lock_dlm.
744	 */
745	queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0);
746}
747
748const struct gfs2_glock_operations gfs2_meta_glops = {
749	.go_type = LM_TYPE_META,
750	.go_flags = GLOF_NONDISK,
751};
752
753const struct gfs2_glock_operations gfs2_inode_glops = {
754	.go_sync = inode_go_sync,
755	.go_inval = inode_go_inval,
756	.go_demote_ok = inode_go_demote_ok,
757	.go_lock = inode_go_lock,
758	.go_dump = inode_go_dump,
759	.go_type = LM_TYPE_INODE,
760	.go_flags = GLOF_ASPACE | GLOF_LRU | GLOF_LVB,
761	.go_free = inode_go_free,
762};
763
764const struct gfs2_glock_operations gfs2_rgrp_glops = {
765	.go_sync = rgrp_go_sync,
766	.go_inval = rgrp_go_inval,
767	.go_lock = gfs2_rgrp_go_lock,
768	.go_dump = gfs2_rgrp_go_dump,
769	.go_type = LM_TYPE_RGRP,
770	.go_flags = GLOF_LVB,
771};
772
773const struct gfs2_glock_operations gfs2_freeze_glops = {
774	.go_sync = freeze_go_sync,
775	.go_xmote_bh = freeze_go_xmote_bh,
776	.go_demote_ok = freeze_go_demote_ok,
777	.go_type = LM_TYPE_NONDISK,
778	.go_flags = GLOF_NONDISK,
779};
780
781const struct gfs2_glock_operations gfs2_iopen_glops = {
782	.go_type = LM_TYPE_IOPEN,
783	.go_callback = iopen_go_callback,
784	.go_demote_ok = iopen_go_demote_ok,
785	.go_flags = GLOF_LRU | GLOF_NONDISK,
786	.go_subclass = 1,
787};
788
789const struct gfs2_glock_operations gfs2_flock_glops = {
790	.go_type = LM_TYPE_FLOCK,
791	.go_flags = GLOF_LRU | GLOF_NONDISK,
792};
793
794const struct gfs2_glock_operations gfs2_nondisk_glops = {
795	.go_type = LM_TYPE_NONDISK,
796	.go_flags = GLOF_NONDISK,
797	.go_callback = nondisk_go_callback,
798};
799
800const struct gfs2_glock_operations gfs2_quota_glops = {
801	.go_type = LM_TYPE_QUOTA,
802	.go_flags = GLOF_LVB | GLOF_LRU | GLOF_NONDISK,
803};
804
805const struct gfs2_glock_operations gfs2_journal_glops = {
806	.go_type = LM_TYPE_JOURNAL,
807	.go_flags = GLOF_NONDISK,
808};
809
810const struct gfs2_glock_operations *gfs2_glops_list[] = {
811	[LM_TYPE_META] = &gfs2_meta_glops,
812	[LM_TYPE_INODE] = &gfs2_inode_glops,
813	[LM_TYPE_RGRP] = &gfs2_rgrp_glops,
814	[LM_TYPE_IOPEN] = &gfs2_iopen_glops,
815	[LM_TYPE_FLOCK] = &gfs2_flock_glops,
816	[LM_TYPE_NONDISK] = &gfs2_nondisk_glops,
817	[LM_TYPE_QUOTA] = &gfs2_quota_glops,
818	[LM_TYPE_JOURNAL] = &gfs2_journal_glops,
819};
820
821