summaryrefslogtreecommitdiff
path: root/fs/btrfs/raid-stripe-tree.c
blob: 9589362acfbf9e2ec3c99fdc4b1fb056bf3ddbc7 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2023 Western Digital Corporation or its affiliates.
 */

#include <linux/btrfs_tree.h>
#include "ctree.h"
#include "fs.h"
#include "accessors.h"
#include "transaction.h"
#include "disk-io.h"
#include "raid-stripe-tree.h"
#include "volumes.h"
#include "misc.h"
#include "print-tree.h"

int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 length)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *stripe_root = fs_info->stripe_root;
	struct btrfs_path *path;
	struct btrfs_key key;
	struct extent_buffer *leaf;
	u64 found_start;
	u64 found_end;
	u64 end = start + length;
	int slot;
	int ret;

	if (!stripe_root)
		return 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	while (1) {
		key.objectid = start;
		key.type = BTRFS_RAID_STRIPE_KEY;
		key.offset = length;

		ret = btrfs_search_slot(trans, stripe_root, &key, path, -1, 1);
		if (ret < 0)
			break;
		if (ret > 0) {
			ret = 0;
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}

		leaf = path->nodes[0];
		slot = path->slots[0];
		btrfs_item_key_to_cpu(leaf, &key, slot);
		found_start = key.objectid;
		found_end = found_start + key.offset;

		/* That stripe ends before we start, we're done. */
		if (found_end <= start)
			break;

		trace_btrfs_raid_extent_delete(fs_info, start, end,
					       found_start, found_end);

		ASSERT(found_start >= start && found_end <= end);
		ret = btrfs_del_item(trans, stripe_root, path);
		if (ret)
			break;

		btrfs_release_path(path);
	}

	btrfs_free_path(path);
	return ret;
}

static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
					struct btrfs_io_context *bioc)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_key stripe_key;
	struct btrfs_root *stripe_root = fs_info->stripe_root;
	const int num_stripes = btrfs_bg_type_to_factor(bioc->map_type);
	u8 encoding = btrfs_bg_flags_to_raid_index(bioc->map_type);
	struct btrfs_stripe_extent *stripe_extent;
	const size_t item_size = struct_size(stripe_extent, strides, num_stripes);
	int ret;

	stripe_extent = kzalloc(item_size, GFP_NOFS);
	if (!stripe_extent) {
		btrfs_abort_transaction(trans, -ENOMEM);
		btrfs_end_transaction(trans);
		return -ENOMEM;
	}

	trace_btrfs_insert_one_raid_extent(fs_info, bioc->logical, bioc->size,
					   num_stripes);
	btrfs_set_stack_stripe_extent_encoding(stripe_extent, encoding);
	for (int i = 0; i < num_stripes; i++) {
		u64 devid = bioc->stripes[i].dev->devid;
		u64 physical = bioc->stripes[i].physical;
		u64 length = bioc->stripes[i].length;
		struct btrfs_raid_stride *raid_stride = &stripe_extent->strides[i];

		if (length == 0)
			length = bioc->size;

		btrfs_set_stack_raid_stride_devid(raid_stride, devid);
		btrfs_set_stack_raid_stride_physical(raid_stride, physical);
	}

	stripe_key.objectid = bioc->logical;
	stripe_key.type = BTRFS_RAID_STRIPE_KEY;
	stripe_key.offset = bioc->size;

	ret = btrfs_insert_item(trans, stripe_root, &stripe_key, stripe_extent,
				item_size);
	if (ret)
		btrfs_abort_transaction(trans, ret);

	kfree(stripe_extent);

	return ret;
}

int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans,
			     struct btrfs_ordered_extent *ordered_extent)
{
	struct btrfs_io_context *bioc;
	int ret;

	if (!btrfs_fs_incompat(trans->fs_info, RAID_STRIPE_TREE))
		return 0;

	list_for_each_entry(bioc, &ordered_extent->bioc_list, rst_ordered_entry) {
		ret = btrfs_insert_one_raid_extent(trans, bioc);
		if (ret)
			return ret;
	}

	while (!list_empty(&ordered_extent->bioc_list)) {
		bioc = list_first_entry(&ordered_extent->bioc_list,
					typeof(*bioc), rst_ordered_entry);
		list_del(&bioc->rst_ordered_entry);
		btrfs_put_bioc(bioc);
	}

	return 0;
}

int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
				 u64 logical, u64 *length, u64 map_type,
				 u32 stripe_index, struct btrfs_io_stripe *stripe)
{
	struct btrfs_root *stripe_root = fs_info->stripe_root;
	struct btrfs_stripe_extent *stripe_extent;
	struct btrfs_key stripe_key;
	struct btrfs_key found_key;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	const u64 end = logical + *length;
	int num_stripes;
	u8 encoding;
	u64 offset;
	u64 found_logical;
	u64 found_length;
	u64 found_end;
	int slot;
	int ret;

	stripe_key.objectid = logical;
	stripe_key.type = BTRFS_RAID_STRIPE_KEY;
	stripe_key.offset = 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	if (stripe->is_scrub) {
		path->skip_locking = 1;
		path->search_commit_root = 1;
	}

	ret = btrfs_search_slot(NULL, stripe_root, &stripe_key, path, 0, 0);
	if (ret < 0)
		goto free_path;
	if (ret) {
		if (path->slots[0] != 0)
			path->slots[0]--;
	}

	while (1) {
		leaf = path->nodes[0];
		slot = path->slots[0];

		btrfs_item_key_to_cpu(leaf, &found_key, slot);
		found_logical = found_key.objectid;
		found_length = found_key.offset;
		found_end = found_logical + found_length;

		if (found_logical > end) {
			ret = -ENOENT;
			goto out;
		}

		if (in_range(logical, found_logical, found_length))
			break;

		ret = btrfs_next_item(stripe_root, path);
		if (ret)
			goto out;
	}

	offset = logical - found_logical;

	/*
	 * If we have a logically contiguous, but physically non-continuous
	 * range, we need to split the bio. Record the length after which we
	 * must split the bio.
	 */
	if (end > found_end)
		*length -= end - found_end;

	num_stripes = btrfs_num_raid_stripes(btrfs_item_size(leaf, slot));
	stripe_extent = btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent);
	encoding = btrfs_stripe_extent_encoding(leaf, stripe_extent);

	if (encoding != btrfs_bg_flags_to_raid_index(map_type)) {
		ret = -EUCLEAN;
		btrfs_handle_fs_error(fs_info, ret,
				      "on-disk stripe encoding %d doesn't match RAID index %d",
				      encoding,
				      btrfs_bg_flags_to_raid_index(map_type));
		goto out;
	}

	for (int i = 0; i < num_stripes; i++) {
		struct btrfs_raid_stride *stride = &stripe_extent->strides[i];
		u64 devid = btrfs_raid_stride_devid(leaf, stride);
		u64 physical = btrfs_raid_stride_physical(leaf, stride);

		if (devid != stripe->dev->devid)
			continue;

		if ((map_type & BTRFS_BLOCK_GROUP_DUP) && stripe_index != i)
			continue;

		stripe->physical = physical + offset;

		trace_btrfs_get_raid_extent_offset(fs_info, logical, *length,
						   stripe->physical, devid);

		ret = 0;
		goto free_path;
	}

	/* If we're here, we haven't found the requested devid in the stripe. */
	ret = -ENOENT;
out:
	if (ret > 0)
		ret = -ENOENT;
	if (ret && ret != -EIO && !stripe->is_scrub) {
		if (IS_ENABLED(CONFIG_BTRFS_DEBUG))
			btrfs_print_tree(leaf, 1);
		btrfs_err(fs_info,
		"cannot find raid-stripe for logical [%llu, %llu] devid %llu, profile %s",
			  logical, logical + *length, stripe->dev->devid,
			  btrfs_bg_type_to_raid_name(map_type));
	}
free_path:
	btrfs_free_path(path);

	return ret;
}