1// SPDX-License-Identifier: GPL-2.0
2/*
3 * Copyright (c) 2000,2005 Silicon Graphics, Inc.
4 * All Rights Reserved.
5 */
6#include "xfs.h"
7#include "xfs_fs.h"
8#include "xfs_shared.h"
9#include "xfs_format.h"
10#include "xfs_log_format.h"
11#include "xfs_trans_resv.h"
12#include "xfs_mount.h"
13#include "xfs_inode.h"
14#include "xfs_trans.h"
15#include "xfs_trans_priv.h"
16#include "xfs_inode_item.h"
17
18#include <linux/iversion.h>
19
20/*
21 * Add a locked inode to the transaction.
22 *
23 * The inode must be locked, and it cannot be associated with any transaction.
24 * If lock_flags is non-zero the inode will be unlocked on transaction commit.
25 */
26void
27xfs_trans_ijoin(
28	struct xfs_trans	*tp,
29	struct xfs_inode	*ip,
30	uint			lock_flags)
31{
32	struct xfs_inode_log_item *iip;
33
34	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
35	if (ip->i_itemp == NULL)
36		xfs_inode_item_init(ip, ip->i_mount);
37	iip = ip->i_itemp;
38
39	ASSERT(iip->ili_lock_flags == 0);
40	iip->ili_lock_flags = lock_flags;
41	ASSERT(!xfs_iflags_test(ip, XFS_ISTALE));
42
43	/*
44	 * Get a log_item_desc to point at the new item.
45	 */
46	xfs_trans_add_item(tp, &iip->ili_item);
47}
48
49/*
50 * Transactional inode timestamp update. Requires the inode to be locked and
51 * joined to the transaction supplied. Relies on the transaction subsystem to
52 * track dirty state and update/writeback the inode accordingly.
53 */
54void
55xfs_trans_ichgtime(
56	struct xfs_trans	*tp,
57	struct xfs_inode	*ip,
58	int			flags)
59{
60	struct inode		*inode = VFS_I(ip);
61	struct timespec64	tv;
62
63	ASSERT(tp);
64	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
65
66	tv = current_time(inode);
67
68	if (flags & XFS_ICHGTIME_MOD)
69		inode->i_mtime = tv;
70	if (flags & XFS_ICHGTIME_CHG)
71		inode->i_ctime = tv;
72	if (flags & XFS_ICHGTIME_CREATE)
73		ip->i_d.di_crtime = tv;
74}
75
76/*
77 * This is called to mark the fields indicated in fieldmask as needing to be
78 * logged when the transaction is committed.  The inode must already be
79 * associated with the given transaction.
80 *
81 * The values for fieldmask are defined in xfs_inode_item.h.  We always log all
82 * of the core inode if any of it has changed, and we always log all of the
83 * inline data/extents/b-tree root if any of them has changed.
84 *
85 * Grab and pin the cluster buffer associated with this inode to avoid RMW
86 * cycles at inode writeback time. Avoid the need to add error handling to every
87 * xfs_trans_log_inode() call by shutting down on read error.  This will cause
88 * transactions to fail and everything to error out, just like if we return a
89 * read error in a dirty transaction and cancel it.
90 */
91void
92xfs_trans_log_inode(
93	struct xfs_trans	*tp,
94	struct xfs_inode	*ip,
95	uint			flags)
96{
97	struct xfs_inode_log_item *iip = ip->i_itemp;
98	struct inode		*inode = VFS_I(ip);
99	uint			iversion_flags = 0;
100
101	ASSERT(iip);
102	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
103	ASSERT(!xfs_iflags_test(ip, XFS_ISTALE));
104
105	tp->t_flags |= XFS_TRANS_DIRTY;
106
107	/*
108	 * Don't bother with i_lock for the I_DIRTY_TIME check here, as races
109	 * don't matter - we either will need an extra transaction in 24 hours
110	 * to log the timestamps, or will clear already cleared fields in the
111	 * worst case.
112	 */
113	if (inode->i_state & I_DIRTY_TIME) {
114		spin_lock(&inode->i_lock);
115		inode->i_state &= ~I_DIRTY_TIME;
116		spin_unlock(&inode->i_lock);
117	}
118
119	/*
120	 * First time we log the inode in a transaction, bump the inode change
121	 * counter if it is configured for this to occur. While we have the
122	 * inode locked exclusively for metadata modification, we can usually
123	 * avoid setting XFS_ILOG_CORE if no one has queried the value since
124	 * the last time it was incremented. If we have XFS_ILOG_CORE already
125	 * set however, then go ahead and bump the i_version counter
126	 * unconditionally.
127	 */
128	if (!test_and_set_bit(XFS_LI_DIRTY, &iip->ili_item.li_flags)) {
129		if (IS_I_VERSION(inode) &&
130		    inode_maybe_inc_iversion(inode, flags & XFS_ILOG_CORE))
131			iversion_flags = XFS_ILOG_CORE;
132	}
133
134	/*
135	 * If we're updating the inode core or the timestamps and it's possible
136	 * to upgrade this inode to bigtime format, do so now.
137	 */
138	if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) &&
139	    xfs_sb_version_hasbigtime(&ip->i_mount->m_sb) &&
140	    !xfs_inode_has_bigtime(ip)) {
141		ip->i_d.di_flags2 |= XFS_DIFLAG2_BIGTIME;
142		flags |= XFS_ILOG_CORE;
143	}
144
145	/*
146	 * Record the specific change for fdatasync optimisation. This allows
147	 * fdatasync to skip log forces for inodes that are only timestamp
148	 * dirty.
149	 */
150	spin_lock(&iip->ili_lock);
151	iip->ili_fsync_fields |= flags;
152
153	if (!iip->ili_item.li_buf) {
154		struct xfs_buf	*bp;
155		int		error;
156
157		/*
158		 * We hold the ILOCK here, so this inode is not going to be
159		 * flushed while we are here. Further, because there is no
160		 * buffer attached to the item, we know that there is no IO in
161		 * progress, so nothing will clear the ili_fields while we read
162		 * in the buffer. Hence we can safely drop the spin lock and
163		 * read the buffer knowing that the state will not change from
164		 * here.
165		 */
166		spin_unlock(&iip->ili_lock);
167		error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, NULL,
168					&bp, 0);
169		if (error) {
170			xfs_force_shutdown(ip->i_mount, SHUTDOWN_META_IO_ERROR);
171			return;
172		}
173
174		/*
175		 * We need an explicit buffer reference for the log item but
176		 * don't want the buffer to remain attached to the transaction.
177		 * Hold the buffer but release the transaction reference once
178		 * we've attached the inode log item to the buffer log item
179		 * list.
180		 */
181		xfs_buf_hold(bp);
182		spin_lock(&iip->ili_lock);
183		iip->ili_item.li_buf = bp;
184		bp->b_flags |= _XBF_INODES;
185		list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list);
186		xfs_trans_brelse(tp, bp);
187	}
188
189	/*
190	 * Always OR in the bits from the ili_last_fields field.  This is to
191	 * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines
192	 * in the eventual clearing of the ili_fields bits.  See the big comment
193	 * in xfs_iflush() for an explanation of this coordination mechanism.
194	 */
195	iip->ili_fields |= (flags | iip->ili_last_fields | iversion_flags);
196	spin_unlock(&iip->ili_lock);
197}
198
199int
200xfs_trans_roll_inode(
201	struct xfs_trans	**tpp,
202	struct xfs_inode	*ip)
203{
204	int			error;
205
206	xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
207	error = xfs_trans_roll(tpp);
208	if (!error)
209		xfs_trans_ijoin(*tpp, ip, 0);
210	return error;
211}
212