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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2010 Red Hat, Inc.
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_discard.h"
#include "xfs_error.h"
#include "xfs_extent_busy.h"
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_ag.h"
STATIC int
xfs_trim_extents(
struct xfs_mount *mp,
xfs_agnumber_t agno,
xfs_daddr_t start,
xfs_daddr_t end,
xfs_daddr_t minlen,
uint64_t *blocks_trimmed)
{
struct block_device *bdev = mp->m_ddev_targp->bt_bdev;
struct xfs_btree_cur *cur;
struct xfs_buf *agbp;
struct xfs_agf *agf;
struct xfs_perag *pag;
int error;
int i;
pag = xfs_perag_get(mp, agno);
/*
* Force out the log. This means any transactions that might have freed
* space before we take the AGF buffer lock are now on disk, and the
* volatile disk cache is flushed.
*/
xfs_log_force(mp, XFS_LOG_SYNC);
error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
if (error)
goto out_put_perag;
agf = agbp->b_addr;
cur = xfs_allocbt_init_cursor(mp, NULL, agbp, pag, XFS_BTNUM_CNT);
/*
* Look up the longest btree in the AGF and start with it.
*/
error = xfs_alloc_lookup_ge(cur, 0, be32_to_cpu(agf->agf_longest), &i);
if (error)
goto out_del_cursor;
/*
* Loop until we are done with all extents that are large
* enough to be worth discarding.
*/
while (i) {
xfs_agblock_t fbno;
xfs_extlen_t flen;
xfs_daddr_t dbno;
xfs_extlen_t dlen;
error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
if (error)
goto out_del_cursor;
if (XFS_IS_CORRUPT(mp, i != 1)) {
error = -EFSCORRUPTED;
goto out_del_cursor;
}
ASSERT(flen <= be32_to_cpu(agf->agf_longest));
/*
* use daddr format for all range/len calculations as that is
* the format the range/len variables are supplied in by
* userspace.
*/
dbno = XFS_AGB_TO_DADDR(mp, agno, fbno);
dlen = XFS_FSB_TO_BB(mp, flen);
/*
* Too small? Give up.
*/
if (dlen < minlen) {
trace_xfs_discard_toosmall(mp, agno, fbno, flen);
goto out_del_cursor;
}
/*
* If the extent is entirely outside of the range we are
* supposed to discard skip it. Do not bother to trim
* down partially overlapping ranges for now.
*/
if (dbno + dlen < start || dbno > end) {
trace_xfs_discard_exclude(mp, agno, fbno, flen);
goto next_extent;
}
/*
* If any blocks in the range are still busy, skip the
* discard and try again the next time.
*/
if (xfs_extent_busy_search(mp, pag, fbno, flen)) {
trace_xfs_discard_busy(mp, agno, fbno, flen);
goto next_extent;
}
trace_xfs_discard_extent(mp, agno, fbno, flen);
error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS, 0);
if (error)
goto out_del_cursor;
*blocks_trimmed += flen;
next_extent:
error = xfs_btree_decrement(cur, 0, &i);
if (error)
goto out_del_cursor;
if (fatal_signal_pending(current)) {
error = -ERESTARTSYS;
goto out_del_cursor;
}
}
out_del_cursor:
xfs_btree_del_cursor(cur, error);
xfs_buf_relse(agbp);
out_put_perag:
xfs_perag_put(pag);
return error;
}
/*
* trim a range of the filesystem.
*
* Note: the parameters passed from userspace are byte ranges into the
* filesystem which does not match to the format we use for filesystem block
* addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
* is a linear address range. Hence we need to use DADDR based conversions and
* comparisons for determining the correct offset and regions to trim.
*/
int
xfs_ioc_trim(
struct xfs_mount *mp,
struct fstrim_range __user *urange)
{
struct request_queue *q = bdev_get_queue(mp->m_ddev_targp->bt_bdev);
unsigned int granularity = q->limits.discard_granularity;
struct fstrim_range range;
xfs_daddr_t start, end, minlen;
xfs_agnumber_t start_agno, end_agno, agno;
uint64_t blocks_trimmed = 0;
int error, last_error = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
/*
* We haven't recovered the log, so we cannot use our bnobt-guided
* storage zapping commands.
*/
if (mp->m_flags & XFS_MOUNT_NORECOVERY)
return -EROFS;
if (copy_from_user(&range, urange, sizeof(range)))
return -EFAULT;
range.minlen = max_t(u64, granularity, range.minlen);
minlen = BTOBB(range.minlen);
/*
* Truncating down the len isn't actually quite correct, but using
* BBTOB would mean we trivially get overflows for values
* of ULLONG_MAX or slightly lower. And ULLONG_MAX is the default
* used by the fstrim application. In the end it really doesn't
* matter as trimming blocks is an advisory interface.
*/
if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) ||
range.minlen > XFS_FSB_TO_B(mp, mp->m_ag_max_usable) ||
range.len < mp->m_sb.sb_blocksize)
return -EINVAL;
start = BTOBB(range.start);
end = start + BTOBBT(range.len) - 1;
if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1;
start_agno = xfs_daddr_to_agno(mp, start);
end_agno = xfs_daddr_to_agno(mp, end);
for (agno = start_agno; agno <= end_agno; agno++) {
error = xfs_trim_extents(mp, agno, start, end, minlen,
&blocks_trimmed);
if (error) {
last_error = error;
if (error == -ERESTARTSYS)
break;
}
}
if (last_error)
return last_error;
range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
if (copy_to_user(urange, &range, sizeof(range)))
return -EFAULT;
return 0;
}
|
