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
|
/*
* Handler for virtio-blk I/O
*
* Copyright (c) 2020 Red Hat, Inc.
* Copyright (C) 2022 Bytedance Inc. and/or its affiliates. All rights reserved.
*
* Author:
* Coiby Xu <coiby.xu@gmail.com>
* Xie Yongji <xieyongji@bytedance.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu/error-report.h"
#include "virtio-blk-handler.h"
#include "standard-headers/linux/virtio_blk.h"
struct virtio_blk_inhdr {
unsigned char status;
};
static bool virtio_blk_sect_range_ok(BlockBackend *blk, uint32_t block_size,
uint64_t sector, size_t size)
{
uint64_t nb_sectors;
uint64_t total_sectors;
if (size % VIRTIO_BLK_SECTOR_SIZE) {
return false;
}
nb_sectors = size >> VIRTIO_BLK_SECTOR_BITS;
QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != VIRTIO_BLK_SECTOR_SIZE);
if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
return false;
}
if ((sector << VIRTIO_BLK_SECTOR_BITS) % block_size) {
return false;
}
blk_get_geometry(blk, &total_sectors);
if (sector > total_sectors || nb_sectors > total_sectors - sector) {
return false;
}
return true;
}
static int coroutine_fn
virtio_blk_discard_write_zeroes(VirtioBlkHandler *handler, struct iovec *iov,
uint32_t iovcnt, uint32_t type)
{
BlockBackend *blk = handler->blk;
struct virtio_blk_discard_write_zeroes desc;
ssize_t size;
uint64_t sector;
uint32_t num_sectors;
uint32_t max_sectors;
uint32_t flags;
int bytes;
/* Only one desc is currently supported */
if (unlikely(iov_size(iov, iovcnt) > sizeof(desc))) {
return VIRTIO_BLK_S_UNSUPP;
}
size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc));
if (unlikely(size != sizeof(desc))) {
error_report("Invalid size %zd, expected %zu", size, sizeof(desc));
return VIRTIO_BLK_S_IOERR;
}
sector = le64_to_cpu(desc.sector);
num_sectors = le32_to_cpu(desc.num_sectors);
flags = le32_to_cpu(desc.flags);
max_sectors = (type == VIRTIO_BLK_T_WRITE_ZEROES) ?
VIRTIO_BLK_MAX_WRITE_ZEROES_SECTORS :
VIRTIO_BLK_MAX_DISCARD_SECTORS;
/* This check ensures that 'bytes' fits in an int */
if (unlikely(num_sectors > max_sectors)) {
return VIRTIO_BLK_S_IOERR;
}
bytes = num_sectors << VIRTIO_BLK_SECTOR_BITS;
if (unlikely(!virtio_blk_sect_range_ok(blk, handler->logical_block_size,
sector, bytes))) {
return VIRTIO_BLK_S_IOERR;
}
/*
* The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for discard
* and write zeroes commands if any unknown flag is set.
*/
if (unlikely(flags & ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) {
return VIRTIO_BLK_S_UNSUPP;
}
if (type == VIRTIO_BLK_T_WRITE_ZEROES) {
int blk_flags = 0;
if (flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) {
blk_flags |= BDRV_REQ_MAY_UNMAP;
}
if (blk_co_pwrite_zeroes(blk, sector << VIRTIO_BLK_SECTOR_BITS,
bytes, blk_flags) == 0) {
return VIRTIO_BLK_S_OK;
}
} else if (type == VIRTIO_BLK_T_DISCARD) {
/*
* The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for
* discard commands if the unmap flag is set.
*/
if (unlikely(flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) {
return VIRTIO_BLK_S_UNSUPP;
}
if (blk_co_pdiscard(blk, sector << VIRTIO_BLK_SECTOR_BITS,
bytes) == 0) {
return VIRTIO_BLK_S_OK;
}
}
return VIRTIO_BLK_S_IOERR;
}
int coroutine_fn virtio_blk_process_req(VirtioBlkHandler *handler,
struct iovec *in_iov,
struct iovec *out_iov,
unsigned int in_num,
unsigned int out_num)
{
BlockBackend *blk = handler->blk;
struct virtio_blk_inhdr *in;
struct virtio_blk_outhdr out;
uint32_t type;
int in_len;
if (out_num < 1 || in_num < 1) {
error_report("virtio-blk request missing headers");
return -EINVAL;
}
if (unlikely(iov_to_buf(out_iov, out_num, 0, &out,
sizeof(out)) != sizeof(out))) {
error_report("virtio-blk request outhdr too short");
return -EINVAL;
}
iov_discard_front(&out_iov, &out_num, sizeof(out));
if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
error_report("virtio-blk request inhdr too short");
return -EINVAL;
}
/* We always touch the last byte, so just see how big in_iov is. */
in_len = iov_size(in_iov, in_num);
in = (void *)in_iov[in_num - 1].iov_base
+ in_iov[in_num - 1].iov_len
- sizeof(struct virtio_blk_inhdr);
iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr));
type = le32_to_cpu(out.type);
switch (type & ~VIRTIO_BLK_T_BARRIER) {
case VIRTIO_BLK_T_IN:
case VIRTIO_BLK_T_OUT: {
QEMUIOVector qiov;
int64_t offset;
ssize_t ret = 0;
bool is_write = type & VIRTIO_BLK_T_OUT;
int64_t sector_num = le64_to_cpu(out.sector);
if (is_write && !handler->writable) {
in->status = VIRTIO_BLK_S_IOERR;
break;
}
if (is_write) {
qemu_iovec_init_external(&qiov, out_iov, out_num);
} else {
qemu_iovec_init_external(&qiov, in_iov, in_num);
}
if (unlikely(!virtio_blk_sect_range_ok(blk,
handler->logical_block_size,
sector_num, qiov.size))) {
in->status = VIRTIO_BLK_S_IOERR;
break;
}
offset = sector_num << VIRTIO_BLK_SECTOR_BITS;
if (is_write) {
ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0);
} else {
ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0);
}
if (ret >= 0) {
in->status = VIRTIO_BLK_S_OK;
} else {
in->status = VIRTIO_BLK_S_IOERR;
}
break;
}
case VIRTIO_BLK_T_FLUSH:
if (blk_co_flush(blk) == 0) {
in->status = VIRTIO_BLK_S_OK;
} else {
in->status = VIRTIO_BLK_S_IOERR;
}
break;
case VIRTIO_BLK_T_GET_ID: {
size_t size = MIN(strlen(handler->serial) + 1,
MIN(iov_size(in_iov, in_num),
VIRTIO_BLK_ID_BYTES));
iov_from_buf(in_iov, in_num, 0, handler->serial, size);
in->status = VIRTIO_BLK_S_OK;
break;
}
case VIRTIO_BLK_T_DISCARD:
case VIRTIO_BLK_T_WRITE_ZEROES:
if (!handler->writable) {
in->status = VIRTIO_BLK_S_IOERR;
break;
}
in->status = virtio_blk_discard_write_zeroes(handler, out_iov,
out_num, type);
break;
default:
in->status = VIRTIO_BLK_S_UNSUPP;
break;
}
return in_len;
}
|
