summaryrefslogtreecommitdiff
path: root/fs/bcachefs/sb-downgrade.c
blob: 3fb23e399ffb3e6c021b8825fe3403e5a048ba4c (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
// SPDX-License-Identifier: GPL-2.0

/*
 * Superblock section that contains a list of recovery passes to run when
 * downgrading past a given version
 */

#include "bcachefs.h"
#include "darray.h"
#include "recovery_passes.h"
#include "sb-downgrade.h"
#include "sb-errors.h"
#include "super-io.h"

#define RECOVERY_PASS_ALL_FSCK		BIT_ULL(63)

/*
 * Upgrade, downgrade tables - run certain recovery passes, fix certain errors
 *
 * x(version, recovery_passes, errors...)
 */
#define UPGRADE_TABLE()						\
	x(backpointers,						\
	  RECOVERY_PASS_ALL_FSCK)				\
	x(inode_v3,						\
	  RECOVERY_PASS_ALL_FSCK)				\
	x(unwritten_extents,					\
	  RECOVERY_PASS_ALL_FSCK)				\
	x(bucket_gens,						\
	  BIT_ULL(BCH_RECOVERY_PASS_bucket_gens_init)|		\
	  RECOVERY_PASS_ALL_FSCK)				\
	x(lru_v2,						\
	  RECOVERY_PASS_ALL_FSCK)				\
	x(fragmentation_lru,					\
	  RECOVERY_PASS_ALL_FSCK)				\
	x(no_bps_in_alloc_keys,					\
	  RECOVERY_PASS_ALL_FSCK)				\
	x(snapshot_trees,					\
	  RECOVERY_PASS_ALL_FSCK)				\
	x(snapshot_skiplists,					\
	  BIT_ULL(BCH_RECOVERY_PASS_check_snapshots),		\
	  BCH_FSCK_ERR_snapshot_bad_depth,			\
	  BCH_FSCK_ERR_snapshot_bad_skiplist)			\
	x(deleted_inodes,					\
	  BIT_ULL(BCH_RECOVERY_PASS_check_inodes),		\
	  BCH_FSCK_ERR_unlinked_inode_not_on_deleted_list)	\
	x(rebalance_work,					\
	  BIT_ULL(BCH_RECOVERY_PASS_set_fs_needs_rebalance))	\
	x(subvolume_fs_parent,					\
	  BIT_ULL(BCH_RECOVERY_PASS_check_dirents),		\
	  BCH_FSCK_ERR_subvol_fs_path_parent_wrong)		\
	x(btree_subvolume_children,				\
	  BIT_ULL(BCH_RECOVERY_PASS_check_subvols),		\
	  BCH_FSCK_ERR_subvol_children_not_set)			\
	x(mi_btree_bitmap,					\
	  BIT_ULL(BCH_RECOVERY_PASS_check_allocations),		\
	  BCH_FSCK_ERR_btree_bitmap_not_marked)

#define DOWNGRADE_TABLE()

struct upgrade_downgrade_entry {
	u64		recovery_passes;
	u16		version;
	u16		nr_errors;
	const u16	*errors;
};

#define x(ver, passes, ...) static const u16 upgrade_##ver##_errors[] = { __VA_ARGS__ };
UPGRADE_TABLE()
#undef x

static const struct upgrade_downgrade_entry upgrade_table[] = {
#define x(ver, passes, ...) {					\
	.recovery_passes	= passes,			\
	.version		= bcachefs_metadata_version_##ver,\
	.nr_errors		= ARRAY_SIZE(upgrade_##ver##_errors),	\
	.errors			= upgrade_##ver##_errors,	\
},
UPGRADE_TABLE()
#undef x
};

void bch2_sb_set_upgrade(struct bch_fs *c,
			 unsigned old_version,
			 unsigned new_version)
{
	lockdep_assert_held(&c->sb_lock);

	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);

	for (const struct upgrade_downgrade_entry *i = upgrade_table;
	     i < upgrade_table + ARRAY_SIZE(upgrade_table);
	     i++)
		if (i->version > old_version && i->version <= new_version) {
			u64 passes = i->recovery_passes;

			if (passes & RECOVERY_PASS_ALL_FSCK)
				passes |= bch2_fsck_recovery_passes();
			passes &= ~RECOVERY_PASS_ALL_FSCK;

			ext->recovery_passes_required[0] |=
				cpu_to_le64(bch2_recovery_passes_to_stable(passes));

			for (const u16 *e = i->errors;
			     e < i->errors + i->nr_errors;
			     e++) {
				__set_bit(*e, c->sb.errors_silent);
				ext->errors_silent[*e / 64] |= cpu_to_le64(BIT_ULL(*e % 64));
			}
		}
}

#define x(ver, passes, ...) static const u16 downgrade_ver_##errors[] = { __VA_ARGS__ };
DOWNGRADE_TABLE()
#undef x

static const struct upgrade_downgrade_entry downgrade_table[] = {
#define x(ver, passes, ...) {					\
	.recovery_passes	= passes,			\
	.version		= bcachefs_metadata_version_##ver,\
	.nr_errors		= ARRAY_SIZE(downgrade_##ver##_errors),	\
	.errors			= downgrade_##ver##_errors,	\
},
DOWNGRADE_TABLE()
#undef x
};

static inline const struct bch_sb_field_downgrade_entry *
downgrade_entry_next_c(const struct bch_sb_field_downgrade_entry *e)
{
	return (void *) &e->errors[le16_to_cpu(e->nr_errors)];
}

#define for_each_downgrade_entry(_d, _i)						\
	for (const struct bch_sb_field_downgrade_entry *_i = (_d)->entries;		\
	     (void *) _i	< vstruct_end(&(_d)->field) &&				\
	     (void *) &_i->errors[0] <= vstruct_end(&(_d)->field) &&			\
	     (void *) downgrade_entry_next_c(_i) <= vstruct_end(&(_d)->field);		\
	     _i = downgrade_entry_next_c(_i))

static int bch2_sb_downgrade_validate(struct bch_sb *sb, struct bch_sb_field *f,
				      enum bch_validate_flags flags, struct printbuf *err)
{
	struct bch_sb_field_downgrade *e = field_to_type(f, downgrade);

	for (const struct bch_sb_field_downgrade_entry *i = e->entries;
	     (void *) i	< vstruct_end(&e->field);
	     i = downgrade_entry_next_c(i)) {
		/*
		 * Careful: sb_field_downgrade_entry is only 2 byte aligned, but
		 * section sizes are 8 byte aligned - an empty entry spanning
		 * the end of the section is allowed (and ignored):
		 */
		if ((void *) &i->errors[0] > vstruct_end(&e->field))
			break;

		if (flags & BCH_VALIDATE_write &&
		    (void *) downgrade_entry_next_c(i) > vstruct_end(&e->field)) {
			prt_printf(err, "downgrade entry overruns end of superblock section");
			return -BCH_ERR_invalid_sb_downgrade;
		}

		if (BCH_VERSION_MAJOR(le16_to_cpu(i->version)) !=
		    BCH_VERSION_MAJOR(le16_to_cpu(sb->version))) {
			prt_printf(err, "downgrade entry with mismatched major version (%u != %u)",
				   BCH_VERSION_MAJOR(le16_to_cpu(i->version)),
				   BCH_VERSION_MAJOR(le16_to_cpu(sb->version)));
			return -BCH_ERR_invalid_sb_downgrade;
		}
	}

	return 0;
}

static void bch2_sb_downgrade_to_text(struct printbuf *out, struct bch_sb *sb,
				      struct bch_sb_field *f)
{
	struct bch_sb_field_downgrade *e = field_to_type(f, downgrade);

	if (out->nr_tabstops <= 1)
		printbuf_tabstop_push(out, 16);

	for_each_downgrade_entry(e, i) {
		prt_str(out, "version:\t");
		bch2_version_to_text(out, le16_to_cpu(i->version));
		prt_newline(out);

		prt_str(out, "recovery passes:\t");
		prt_bitflags(out, bch2_recovery_passes,
			     bch2_recovery_passes_from_stable(le64_to_cpu(i->recovery_passes[0])));
		prt_newline(out);

		prt_str(out, "errors:\t");
		bool first = true;
		for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) {
			if (!first)
				prt_char(out, ',');
			first = false;
			unsigned e = le16_to_cpu(i->errors[j]);
			prt_str(out, e < BCH_SB_ERR_MAX ? bch2_sb_error_strs[e] : "(unknown)");
		}
		prt_newline(out);
	}
}

const struct bch_sb_field_ops bch_sb_field_ops_downgrade = {
	.validate	= bch2_sb_downgrade_validate,
	.to_text	= bch2_sb_downgrade_to_text,
};

int bch2_sb_downgrade_update(struct bch_fs *c)
{
	darray_char table = {};
	int ret = 0;

	for (const struct upgrade_downgrade_entry *src = downgrade_table;
	     src < downgrade_table + ARRAY_SIZE(downgrade_table);
	     src++) {
		if (BCH_VERSION_MAJOR(src->version) != BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version)))
			continue;

		struct bch_sb_field_downgrade_entry *dst;
		unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * src->nr_errors;

		ret = darray_make_room(&table, bytes);
		if (ret)
			goto out;

		dst = (void *) &darray_top(table);
		dst->version = cpu_to_le16(src->version);
		dst->recovery_passes[0]	= cpu_to_le64(src->recovery_passes);
		dst->recovery_passes[1]	= 0;
		dst->nr_errors		= cpu_to_le16(src->nr_errors);
		for (unsigned i = 0; i < src->nr_errors; i++)
			dst->errors[i] = cpu_to_le16(src->errors[i]);

		table.nr += bytes;
	}

	struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade);

	unsigned sb_u64s = DIV_ROUND_UP(sizeof(*d) + table.nr, sizeof(u64));

	if (d && le32_to_cpu(d->field.u64s) > sb_u64s)
		goto out;

	d = bch2_sb_field_resize(&c->disk_sb, downgrade, sb_u64s);
	if (!d) {
		ret = -BCH_ERR_ENOSPC_sb_downgrade;
		goto out;
	}

	memcpy(d->entries, table.data, table.nr);
	memset_u64s_tail(d->entries, 0, table.nr);
out:
	darray_exit(&table);
	return ret;
}

void bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_minor)
{
	struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade);
	if (!d)
		return;

	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);

	for_each_downgrade_entry(d, i) {
		unsigned minor = BCH_VERSION_MINOR(le16_to_cpu(i->version));
		if (new_minor < minor && minor <= old_minor) {
			ext->recovery_passes_required[0] |= i->recovery_passes[0];
			ext->recovery_passes_required[1] |= i->recovery_passes[1];

			for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) {
				unsigned e = le16_to_cpu(i->errors[j]);
				if (e < BCH_SB_ERR_MAX)
					__set_bit(e, c->sb.errors_silent);
				if (e < sizeof(ext->errors_silent) * 8)
					__set_bit_le64(e, ext->errors_silent);
			}
		}
	}
}