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
|
/*
* QEMU Enhanced Disk Format Table I/O
*
* Copyright IBM, Corp. 2010
*
* Authors:
* Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU LGPL, version 2 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
#include "qed.h"
#include "qemu/bswap.h"
/* Called either from qed_check or with table_lock held. */
static int qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table)
{
QEMUIOVector qiov;
int noffsets;
int i, ret;
struct iovec iov = {
.iov_base = table->offsets,
.iov_len = s->header.cluster_size * s->header.table_size,
};
qemu_iovec_init_external(&qiov, &iov, 1);
trace_qed_read_table(s, offset, table);
if (qemu_in_coroutine()) {
qemu_co_mutex_unlock(&s->table_lock);
}
ret = bdrv_preadv(s->bs->file, offset, &qiov);
if (qemu_in_coroutine()) {
qemu_co_mutex_lock(&s->table_lock);
}
if (ret < 0) {
goto out;
}
/* Byteswap offsets */
noffsets = qiov.size / sizeof(uint64_t);
for (i = 0; i < noffsets; i++) {
table->offsets[i] = le64_to_cpu(table->offsets[i]);
}
ret = 0;
out:
/* Completion */
trace_qed_read_table_cb(s, table, ret);
return ret;
}
/**
* Write out an updated part or all of a table
*
* @s: QED state
* @offset: Offset of table in image file, in bytes
* @table: Table
* @index: Index of first element
* @n: Number of elements
* @flush: Whether or not to sync to disk
*
* Called either from qed_check or with table_lock held.
*/
static int qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
unsigned int index, unsigned int n, bool flush)
{
unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1;
unsigned int start, end, i;
QEDTable *new_table;
struct iovec iov;
QEMUIOVector qiov;
size_t len_bytes;
int ret;
trace_qed_write_table(s, offset, table, index, n);
/* Calculate indices of the first and one after last elements */
start = index & ~sector_mask;
end = (index + n + sector_mask) & ~sector_mask;
len_bytes = (end - start) * sizeof(uint64_t);
new_table = qemu_blockalign(s->bs, len_bytes);
iov = (struct iovec) {
.iov_base = new_table->offsets,
.iov_len = len_bytes,
};
qemu_iovec_init_external(&qiov, &iov, 1);
/* Byteswap table */
for (i = start; i < end; i++) {
uint64_t le_offset = cpu_to_le64(table->offsets[i]);
new_table->offsets[i - start] = le_offset;
}
/* Adjust for offset into table */
offset += start * sizeof(uint64_t);
if (qemu_in_coroutine()) {
qemu_co_mutex_unlock(&s->table_lock);
}
ret = bdrv_pwritev(s->bs->file, offset, &qiov);
if (qemu_in_coroutine()) {
qemu_co_mutex_lock(&s->table_lock);
}
trace_qed_write_table_cb(s, table, flush, ret);
if (ret < 0) {
goto out;
}
if (flush) {
ret = bdrv_flush(s->bs);
if (ret < 0) {
goto out;
}
}
ret = 0;
out:
qemu_vfree(new_table);
return ret;
}
int qed_read_l1_table_sync(BDRVQEDState *s)
{
return qed_read_table(s, s->header.l1_table_offset, s->l1_table);
}
/* Called either from qed_check or with table_lock held. */
int qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n)
{
BLKDBG_EVENT(s->bs->file, BLKDBG_L1_UPDATE);
return qed_write_table(s, s->header.l1_table_offset,
s->l1_table, index, n, false);
}
int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
unsigned int n)
{
return qed_write_l1_table(s, index, n);
}
/* Called either from qed_check or with table_lock held. */
int qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset)
{
int ret;
qed_unref_l2_cache_entry(request->l2_table);
/* Check for cached L2 entry */
request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, offset);
if (request->l2_table) {
return 0;
}
request->l2_table = qed_alloc_l2_cache_entry(&s->l2_cache);
request->l2_table->table = qed_alloc_table(s);
BLKDBG_EVENT(s->bs->file, BLKDBG_L2_LOAD);
ret = qed_read_table(s, offset, request->l2_table->table);
if (ret) {
/* can't trust loaded L2 table anymore */
qed_unref_l2_cache_entry(request->l2_table);
request->l2_table = NULL;
} else {
request->l2_table->offset = offset;
qed_commit_l2_cache_entry(&s->l2_cache, request->l2_table);
/* This is guaranteed to succeed because we just committed the entry
* to the cache.
*/
request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, offset);
assert(request->l2_table != NULL);
}
return ret;
}
int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset)
{
return qed_read_l2_table(s, request, offset);
}
/* Called either from qed_check or with table_lock held. */
int qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
unsigned int index, unsigned int n, bool flush)
{
BLKDBG_EVENT(s->bs->file, BLKDBG_L2_UPDATE);
return qed_write_table(s, request->l2_table->offset,
request->l2_table->table, index, n, flush);
}
int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
unsigned int index, unsigned int n, bool flush)
{
return qed_write_l2_table(s, request, index, n, flush);
}
|
