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
|
/*
* Communication channel between QEMU and remote device process
*
* Copyright © 2018, 2021 Oracle and/or its affiliates.
*
* 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-common.h"
#include "qemu/module.h"
#include "hw/remote/mpqemu-link.h"
#include "qapi/error.h"
#include "qemu/iov.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "io/channel.h"
#include "sysemu/iothread.h"
#include "trace.h"
/*
* Send message over the ioc QIOChannel.
* This function is safe to call from:
* - main loop in co-routine context. Will block the main loop if not in
* co-routine context;
* - vCPU thread with no co-routine context and if the channel is not part
* of the main loop handling;
* - IOThread within co-routine context, outside of co-routine context
* will block IOThread;
* Returns true if no errors were encountered, false otherwise.
*/
bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
{
ERRP_GUARD();
bool iolock = qemu_mutex_iothread_locked();
bool iothread = qemu_in_iothread();
struct iovec send[2] = {};
int *fds = NULL;
size_t nfds = 0;
bool ret = false;
send[0].iov_base = msg;
send[0].iov_len = MPQEMU_MSG_HDR_SIZE;
send[1].iov_base = (void *)&msg->data;
send[1].iov_len = msg->size;
if (msg->num_fds) {
nfds = msg->num_fds;
fds = msg->fds;
}
/*
* Dont use in IOThread out of co-routine context as
* it will block IOThread.
*/
assert(qemu_in_coroutine() || !iothread);
/*
* Skip unlocking/locking iothread lock when the IOThread is running
* in co-routine context. Co-routine context is asserted above
* for IOThread case.
* Also skip lock handling while in a co-routine in the main context.
*/
if (iolock && !iothread && !qemu_in_coroutine()) {
qemu_mutex_unlock_iothread();
}
if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send),
fds, nfds, errp)) {
ret = true;
} else {
trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds);
}
if (iolock && !iothread && !qemu_in_coroutine()) {
/* See above comment why skip locking here. */
qemu_mutex_lock_iothread();
}
return ret;
}
/*
* Read message from the ioc QIOChannel.
* This function is safe to call from:
* - From main loop in co-routine context. Will block the main loop if not in
* co-routine context;
* - From vCPU thread with no co-routine context and if the channel is not part
* of the main loop handling;
* - From IOThread within co-routine context, outside of co-routine context
* will block IOThread;
*/
static ssize_t mpqemu_read(QIOChannel *ioc, void *buf, size_t len, int **fds,
size_t *nfds, Error **errp)
{
ERRP_GUARD();
struct iovec iov = { .iov_base = buf, .iov_len = len };
bool iolock = qemu_mutex_iothread_locked();
bool iothread = qemu_in_iothread();
int ret = -1;
/*
* Dont use in IOThread out of co-routine context as
* it will block IOThread.
*/
assert(qemu_in_coroutine() || !iothread);
if (iolock && !iothread && !qemu_in_coroutine()) {
qemu_mutex_unlock_iothread();
}
ret = qio_channel_readv_full_all_eof(ioc, &iov, 1, fds, nfds, errp);
if (iolock && !iothread && !qemu_in_coroutine()) {
qemu_mutex_lock_iothread();
}
return (ret <= 0) ? ret : iov.iov_len;
}
bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
{
ERRP_GUARD();
g_autofree int *fds = NULL;
size_t nfds = 0;
ssize_t len;
bool ret = false;
len = mpqemu_read(ioc, msg, MPQEMU_MSG_HDR_SIZE, &fds, &nfds, errp);
if (len <= 0) {
goto fail;
} else if (len != MPQEMU_MSG_HDR_SIZE) {
error_setg(errp, "Message header corrupted");
goto fail;
}
if (msg->size > sizeof(msg->data)) {
error_setg(errp, "Invalid size for message");
goto fail;
}
if (!msg->size) {
goto copy_fds;
}
len = mpqemu_read(ioc, &msg->data, msg->size, NULL, NULL, errp);
if (len <= 0) {
goto fail;
}
if (len != msg->size) {
error_setg(errp, "Unable to read full message");
goto fail;
}
copy_fds:
msg->num_fds = nfds;
if (nfds > G_N_ELEMENTS(msg->fds)) {
error_setg(errp,
"Overflow error: received %zu fds, more than max of %d fds",
nfds, REMOTE_MAX_FDS);
goto fail;
}
if (nfds) {
memcpy(msg->fds, fds, nfds * sizeof(int));
}
ret = true;
fail:
if (*errp) {
trace_mpqemu_recv_io_error(msg->cmd, msg->size, nfds);
}
while (*errp && nfds) {
close(fds[nfds - 1]);
nfds--;
}
return ret;
}
/*
* Send msg and wait for a reply with command code RET_MSG.
* Returns the message received of size u64 or UINT64_MAX
* on error.
* Called from VCPU thread in non-coroutine context.
* Used by the Proxy object to communicate to remote processes.
*/
uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev,
Error **errp)
{
ERRP_GUARD();
MPQemuMsg msg_reply = {0};
uint64_t ret = UINT64_MAX;
assert(!qemu_in_coroutine());
QEMU_LOCK_GUARD(&pdev->io_mutex);
if (!mpqemu_msg_send(msg, pdev->ioc, errp)) {
return ret;
}
if (!mpqemu_msg_recv(&msg_reply, pdev->ioc, errp)) {
return ret;
}
if (!mpqemu_msg_valid(&msg_reply) || msg_reply.cmd != MPQEMU_CMD_RET) {
error_setg(errp, "ERROR: Invalid reply received for command %d",
msg->cmd);
return ret;
}
return msg_reply.data.u64;
}
bool mpqemu_msg_valid(MPQemuMsg *msg)
{
if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) {
return false;
}
/* Verify FDs. */
if (msg->num_fds >= REMOTE_MAX_FDS) {
return false;
}
if (msg->num_fds > 0) {
for (int i = 0; i < msg->num_fds; i++) {
if (fcntl(msg->fds[i], F_GETFL) == -1) {
return false;
}
}
}
/* Verify message specific fields. */
switch (msg->cmd) {
case MPQEMU_CMD_SYNC_SYSMEM:
if (msg->num_fds == 0 || msg->size != sizeof(SyncSysmemMsg)) {
return false;
}
break;
case MPQEMU_CMD_PCI_CFGWRITE:
case MPQEMU_CMD_PCI_CFGREAD:
if (msg->size != sizeof(PciConfDataMsg)) {
return false;
}
break;
case MPQEMU_CMD_BAR_WRITE:
case MPQEMU_CMD_BAR_READ:
if ((msg->size != sizeof(BarAccessMsg)) || (msg->num_fds != 0)) {
return false;
}
break;
case MPQEMU_CMD_SET_IRQFD:
if (msg->size || (msg->num_fds != 2)) {
return false;
}
break;
default:
break;
}
return true;
}
|