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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2007, 2008, 2009 Oracle Corporation
* Written by: Martin K. Petersen <martin.petersen@oracle.com>
*
* Automatically generate and verify integrity data on PI capable devices if the
* bio submitter didn't provide PI itself. This ensures that kernel verifies
* data integrity even if the file system (or other user of the block device) is
* not aware of PI.
*/
#include <linux/blk-integrity.h>
#include <linux/workqueue.h>
#include "blk.h"
struct bio_integrity_data {
struct bio *bio;
struct bvec_iter saved_bio_iter;
struct work_struct work;
struct bio_integrity_payload bip;
struct bio_vec bvec;
};
static struct kmem_cache *bid_slab;
static mempool_t bid_pool;
static struct workqueue_struct *kintegrityd_wq;
static void bio_integrity_finish(struct bio_integrity_data *bid)
{
bid->bio->bi_integrity = NULL;
bid->bio->bi_opf &= ~REQ_INTEGRITY;
kfree(bvec_virt(bid->bip.bip_vec));
mempool_free(bid, &bid_pool);
}
static void bio_integrity_verify_fn(struct work_struct *work)
{
struct bio_integrity_data *bid =
container_of(work, struct bio_integrity_data, work);
struct bio *bio = bid->bio;
blk_integrity_verify_iter(bio, &bid->saved_bio_iter);
bio_integrity_finish(bid);
bio_endio(bio);
}
/**
* __bio_integrity_endio - Integrity I/O completion function
* @bio: Protected bio
*
* Normally I/O completion is done in interrupt context. However, verifying I/O
* integrity is a time-consuming task which must be run in process context.
*
* This function postpones completion accordingly.
*/
bool __bio_integrity_endio(struct bio *bio)
{
struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
struct bio_integrity_payload *bip = bio_integrity(bio);
struct bio_integrity_data *bid =
container_of(bip, struct bio_integrity_data, bip);
if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) {
INIT_WORK(&bid->work, bio_integrity_verify_fn);
queue_work(kintegrityd_wq, &bid->work);
return false;
}
bio_integrity_finish(bid);
return true;
}
/**
* bio_integrity_prep - Prepare bio for integrity I/O
* @bio: bio to prepare
*
* Checks if the bio already has an integrity payload attached. If it does, the
* payload has been generated by another kernel subsystem, and we just pass it
* through.
* Otherwise allocates integrity payload and for writes the integrity metadata
* will be generated. For reads, the completion handler will verify the
* metadata.
*/
bool bio_integrity_prep(struct bio *bio)
{
struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
struct bio_integrity_data *bid;
gfp_t gfp = GFP_NOIO;
unsigned int len;
void *buf;
if (!bi)
return true;
if (!bio_sectors(bio))
return true;
/* Already protected? */
if (bio_integrity(bio))
return true;
switch (bio_op(bio)) {
case REQ_OP_READ:
if (bi->flags & BLK_INTEGRITY_NOVERIFY)
return true;
break;
case REQ_OP_WRITE:
if (bi->flags & BLK_INTEGRITY_NOGENERATE)
return true;
/*
* Zero the memory allocated to not leak uninitialized kernel
* memory to disk for non-integrity metadata where nothing else
* initializes the memory.
*/
if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
gfp |= __GFP_ZERO;
break;
default:
return true;
}
if (WARN_ON_ONCE(bio_has_crypt_ctx(bio)))
return true;
/* Allocate kernel buffer for protection data */
len = bio_integrity_bytes(bi, bio_sectors(bio));
buf = kmalloc(len, gfp);
if (!buf)
goto err_end_io;
bid = mempool_alloc(&bid_pool, GFP_NOIO);
if (!bid)
goto err_free_buf;
bio_integrity_init(bio, &bid->bip, &bid->bvec, 1);
bid->bio = bio;
bid->bip.bip_flags |= BIP_BLOCK_INTEGRITY;
bip_set_seed(&bid->bip, bio->bi_iter.bi_sector);
if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
bid->bip.bip_flags |= BIP_IP_CHECKSUM;
if (bi->csum_type)
bid->bip.bip_flags |= BIP_CHECK_GUARD;
if (bi->flags & BLK_INTEGRITY_REF_TAG)
bid->bip.bip_flags |= BIP_CHECK_REFTAG;
if (bio_integrity_add_page(bio, virt_to_page(buf), len,
offset_in_page(buf)) < len)
goto err_end_io;
/* Auto-generate integrity metadata if this is a write */
if (bio_data_dir(bio) == WRITE)
blk_integrity_generate(bio);
else
bid->saved_bio_iter = bio->bi_iter;
return true;
err_free_buf:
kfree(buf);
err_end_io:
bio->bi_status = BLK_STS_RESOURCE;
bio_endio(bio);
return false;
}
EXPORT_SYMBOL(bio_integrity_prep);
void blk_flush_integrity(void)
{
flush_workqueue(kintegrityd_wq);
}
static int __init blk_integrity_auto_init(void)
{
bid_slab = kmem_cache_create("bio_integrity_data",
sizeof(struct bio_integrity_data), 0,
SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
if (mempool_init_slab_pool(&bid_pool, BIO_POOL_SIZE, bid_slab))
panic("bio: can't create integrity pool\n");
/*
* kintegrityd won't block much but may burn a lot of CPU cycles.
* Make it highpri CPU intensive wq with max concurrency of 1.
*/
kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM |
WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1);
if (!kintegrityd_wq)
panic("Failed to create kintegrityd\n");
return 0;
}
subsys_initcall(blk_integrity_auto_init);
|