summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_notify_failure.c
blob: fa50e5308292d3eaf2e77b0aafef5848e5ed18fe (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2022 Fujitsu.  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_alloc.h"
#include "xfs_bit.h"
#include "xfs_btree.h"
#include "xfs_inode.h"
#include "xfs_icache.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_rtalloc.h"
#include "xfs_trans.h"
#include "xfs_ag.h"

#include <linux/mm.h>
#include <linux/dax.h>
#include <linux/fs.h>

struct xfs_failure_info {
	xfs_agblock_t		startblock;
	xfs_extlen_t		blockcount;
	int			mf_flags;
	bool			want_shutdown;
};

static pgoff_t
xfs_failure_pgoff(
	struct xfs_mount		*mp,
	const struct xfs_rmap_irec	*rec,
	const struct xfs_failure_info	*notify)
{
	loff_t				pos = XFS_FSB_TO_B(mp, rec->rm_offset);

	if (notify->startblock > rec->rm_startblock)
		pos += XFS_FSB_TO_B(mp,
				notify->startblock - rec->rm_startblock);
	return pos >> PAGE_SHIFT;
}

static unsigned long
xfs_failure_pgcnt(
	struct xfs_mount		*mp,
	const struct xfs_rmap_irec	*rec,
	const struct xfs_failure_info	*notify)
{
	xfs_agblock_t			end_rec;
	xfs_agblock_t			end_notify;
	xfs_agblock_t			start_cross;
	xfs_agblock_t			end_cross;

	start_cross = max(rec->rm_startblock, notify->startblock);

	end_rec = rec->rm_startblock + rec->rm_blockcount;
	end_notify = notify->startblock + notify->blockcount;
	end_cross = min(end_rec, end_notify);

	return XFS_FSB_TO_B(mp, end_cross - start_cross) >> PAGE_SHIFT;
}

static int
xfs_dax_failure_fn(
	struct xfs_btree_cur		*cur,
	const struct xfs_rmap_irec	*rec,
	void				*data)
{
	struct xfs_mount		*mp = cur->bc_mp;
	struct xfs_inode		*ip;
	struct xfs_failure_info		*notify = data;
	struct address_space		*mapping;
	pgoff_t				pgoff;
	unsigned long			pgcnt;
	int				error = 0;

	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
	    (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
		/* Continue the query because this isn't a failure. */
		if (notify->mf_flags & MF_MEM_PRE_REMOVE)
			return 0;
		notify->want_shutdown = true;
		return 0;
	}

	/* Get files that incore, filter out others that are not in use. */
	error = xfs_iget(mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE,
			 0, &ip);
	/* Continue the rmap query if the inode isn't incore */
	if (error == -ENODATA)
		return 0;
	if (error) {
		notify->want_shutdown = true;
		return 0;
	}

	mapping = VFS_I(ip)->i_mapping;
	pgoff = xfs_failure_pgoff(mp, rec, notify);
	pgcnt = xfs_failure_pgcnt(mp, rec, notify);

	/* Continue the rmap query if the inode isn't a dax file. */
	if (dax_mapping(mapping))
		error = mf_dax_kill_procs(mapping, pgoff, pgcnt,
					  notify->mf_flags);

	/* Invalidate the cache in dax pages. */
	if (notify->mf_flags & MF_MEM_PRE_REMOVE)
		invalidate_inode_pages2_range(mapping, pgoff,
					      pgoff + pgcnt - 1);

	xfs_irele(ip);
	return error;
}

static int
xfs_dax_notify_failure_freeze(
	struct xfs_mount	*mp)
{
	struct super_block	*sb = mp->m_super;
	int			error;

	error = freeze_super(sb, FREEZE_HOLDER_KERNEL);
	if (error)
		xfs_emerg(mp, "already frozen by kernel, err=%d", error);

	return error;
}

static void
xfs_dax_notify_failure_thaw(
	struct xfs_mount	*mp,
	bool			kernel_frozen)
{
	struct super_block	*sb = mp->m_super;
	int			error;

	if (kernel_frozen) {
		error = thaw_super(sb, FREEZE_HOLDER_KERNEL);
		if (error)
			xfs_emerg(mp, "still frozen after notify failure, err=%d",
				error);
	}

	/*
	 * Also thaw userspace call anyway because the device is about to be
	 * removed immediately.
	 */
	thaw_super(sb, FREEZE_HOLDER_USERSPACE);
}

static int
xfs_dax_notify_ddev_failure(
	struct xfs_mount	*mp,
	xfs_daddr_t		daddr,
	xfs_daddr_t		bblen,
	int			mf_flags)
{
	struct xfs_failure_info	notify = { .mf_flags = mf_flags };
	struct xfs_trans	*tp = NULL;
	struct xfs_btree_cur	*cur = NULL;
	struct xfs_buf		*agf_bp = NULL;
	int			error = 0;
	bool			kernel_frozen = false;
	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, daddr);
	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp,
							     daddr + bblen - 1);
	xfs_agnumber_t		end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);

	if (mf_flags & MF_MEM_PRE_REMOVE) {
		xfs_info(mp, "Device is about to be removed!");
		/*
		 * Freeze fs to prevent new mappings from being created.
		 * - Keep going on if others already hold the kernel forzen.
		 * - Keep going on if other errors too because this device is
		 *   starting to fail.
		 * - If kernel frozen state is hold successfully here, thaw it
		 *   here as well at the end.
		 */
		kernel_frozen = xfs_dax_notify_failure_freeze(mp) == 0;
	}

	error = xfs_trans_alloc_empty(mp, &tp);
	if (error)
		goto out;

	for (; agno <= end_agno; agno++) {
		struct xfs_rmap_irec	ri_low = { };
		struct xfs_rmap_irec	ri_high;
		struct xfs_agf		*agf;
		struct xfs_perag	*pag;
		xfs_agblock_t		range_agend;

		pag = xfs_perag_get(mp, agno);
		error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
		if (error) {
			xfs_perag_put(pag);
			break;
		}

		cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag);

		/*
		 * Set the rmap range from ri_low to ri_high, which represents
		 * a [start, end] where we looking for the files or metadata.
		 */
		memset(&ri_high, 0xFF, sizeof(ri_high));
		ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno);
		if (agno == end_agno)
			ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno);

		agf = agf_bp->b_addr;
		range_agend = min(be32_to_cpu(agf->agf_length) - 1,
				ri_high.rm_startblock);
		notify.startblock = ri_low.rm_startblock;
		notify.blockcount = range_agend + 1 - ri_low.rm_startblock;

		error = xfs_rmap_query_range(cur, &ri_low, &ri_high,
				xfs_dax_failure_fn, &notify);
		xfs_btree_del_cursor(cur, error);
		xfs_trans_brelse(tp, agf_bp);
		xfs_perag_put(pag);
		if (error)
			break;

		fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0);
	}

	xfs_trans_cancel(tp);

	/*
	 * Shutdown fs from a force umount in pre-remove case which won't fail,
	 * so errors can be ignored.  Otherwise, shutdown the filesystem with
	 * CORRUPT flag if error occured or notify.want_shutdown was set during
	 * RMAP querying.
	 */
	if (mf_flags & MF_MEM_PRE_REMOVE)
		xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
	else if (error || notify.want_shutdown) {
		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
		if (!error)
			error = -EFSCORRUPTED;
	}

out:
	/* Thaw the fs if it has been frozen before. */
	if (mf_flags & MF_MEM_PRE_REMOVE)
		xfs_dax_notify_failure_thaw(mp, kernel_frozen);

	return error;
}

static int
xfs_dax_notify_failure(
	struct dax_device	*dax_dev,
	u64			offset,
	u64			len,
	int			mf_flags)
{
	struct xfs_mount	*mp = dax_holder(dax_dev);
	u64			ddev_start;
	u64			ddev_end;

	if (!(mp->m_super->s_flags & SB_BORN)) {
		xfs_warn(mp, "filesystem is not ready for notify_failure()!");
		return -EIO;
	}

	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) {
		xfs_debug(mp,
			 "notify_failure() not supported on realtime device!");
		return -EOPNOTSUPP;
	}

	if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
	    mp->m_logdev_targp != mp->m_ddev_targp) {
		/*
		 * In the pre-remove case the failure notification is attempting
		 * to trigger a force unmount.  The expectation is that the
		 * device is still present, but its removal is in progress and
		 * can not be cancelled, proceed with accessing the log device.
		 */
		if (mf_flags & MF_MEM_PRE_REMOVE)
			return 0;
		xfs_err(mp, "ondisk log corrupt, shutting down fs!");
		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
		return -EFSCORRUPTED;
	}

	if (!xfs_has_rmapbt(mp)) {
		xfs_debug(mp, "notify_failure() needs rmapbt enabled!");
		return -EOPNOTSUPP;
	}

	ddev_start = mp->m_ddev_targp->bt_dax_part_off;
	ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;

	/* Notify failure on the whole device. */
	if (offset == 0 && len == U64_MAX) {
		offset = ddev_start;
		len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev);
	}

	/* Ignore the range out of filesystem area */
	if (offset + len - 1 < ddev_start)
		return -ENXIO;
	if (offset > ddev_end)
		return -ENXIO;

	/* Calculate the real range when it touches the boundary */
	if (offset > ddev_start)
		offset -= ddev_start;
	else {
		len -= ddev_start - offset;
		offset = 0;
	}
	if (offset + len - 1 > ddev_end)
		len = ddev_end - offset + 1;

	return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
			mf_flags);
}

const struct dax_holder_operations xfs_dax_holder_operations = {
	.notify_failure		= xfs_dax_notify_failure,
};