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
275
276
277
278
279
280
|
/*
* QEMU live migration
*
* Copyright IBM, Corp. 2008
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#ifndef QEMU_MIGRATION_H
#define QEMU_MIGRATION_H
#include "qemu-common.h"
#include "qapi/qapi-types-migration.h"
#include "qemu/thread.h"
#include "exec/cpu-common.h"
#include "qemu/coroutine_int.h"
#include "hw/qdev.h"
#include "io/channel.h"
struct PostcopyBlocktimeContext;
#define MIGRATION_RESUME_ACK_VALUE (1)
/* State for the incoming migration */
struct MigrationIncomingState {
QEMUFile *from_src_file;
/*
* Free at the start of the main state load, set as the main thread finishes
* loading state.
*/
QemuEvent main_thread_load_event;
size_t largest_page_size;
bool have_fault_thread;
QemuThread fault_thread;
QemuSemaphore fault_thread_sem;
/* Set this when we want the fault thread to quit */
bool fault_thread_quit;
bool have_listen_thread;
QemuThread listen_thread;
QemuSemaphore listen_thread_sem;
/* For the kernel to send us notifications */
int userfault_fd;
/* To notify the fault_thread to wake, e.g., when need to quit */
int userfault_event_fd;
QEMUFile *to_src_file;
QemuMutex rp_mutex; /* We send replies from multiple threads */
/* RAMBlock of last request sent to source */
RAMBlock *last_rb;
void *postcopy_tmp_page;
void *postcopy_tmp_zero_page;
/* PostCopyFD's for external userfaultfds & handlers of shared memory */
GArray *postcopy_remote_fds;
QEMUBH *bh;
int state;
bool have_colo_incoming_thread;
QemuThread colo_incoming_thread;
/* The coroutine we should enter (back) after failover */
Coroutine *migration_incoming_co;
QemuSemaphore colo_incoming_sem;
/*
* PostcopyBlocktimeContext to keep information for postcopy
* live migration, to calculate vCPU block time
* */
struct PostcopyBlocktimeContext *blocktime_ctx;
/* notify PAUSED postcopy incoming migrations to try to continue */
bool postcopy_recover_triggered;
QemuSemaphore postcopy_pause_sem_dst;
QemuSemaphore postcopy_pause_sem_fault;
};
MigrationIncomingState *migration_incoming_get_current(void);
void migration_incoming_state_destroy(void);
/*
* Functions to work with blocktime context
*/
void fill_destination_postcopy_migration_info(MigrationInfo *info);
#define TYPE_MIGRATION "migration"
#define MIGRATION_CLASS(klass) \
OBJECT_CLASS_CHECK(MigrationClass, (klass), TYPE_MIGRATION)
#define MIGRATION_OBJ(obj) \
OBJECT_CHECK(MigrationState, (obj), TYPE_MIGRATION)
#define MIGRATION_GET_CLASS(obj) \
OBJECT_GET_CLASS(MigrationClass, (obj), TYPE_MIGRATION)
typedef struct MigrationClass {
/*< private >*/
DeviceClass parent_class;
} MigrationClass;
struct MigrationState
{
/*< private >*/
DeviceState parent_obj;
/*< public >*/
size_t bytes_xfer;
size_t xfer_limit;
QemuThread thread;
QEMUBH *cleanup_bh;
QEMUFile *to_dst_file;
/*
* Protects to_dst_file pointer. We need to make sure we won't
* yield or hang during the critical section, since this lock will
* be used in OOB command handler.
*/
QemuMutex qemu_file_lock;
/* bytes already send at the beggining of current interation */
uint64_t iteration_initial_bytes;
/* time at the start of current iteration */
int64_t iteration_start_time;
/*
* The final stage happens when the remaining data is smaller than
* this threshold; it's calculated from the requested downtime and
* measured bandwidth
*/
int64_t threshold_size;
/* params from 'migrate-set-parameters' */
MigrationParameters parameters;
int state;
/* State related to return path */
struct {
QEMUFile *from_dst_file;
QemuThread rp_thread;
bool error;
QemuSemaphore rp_sem;
} rp_state;
double mbps;
/* Timestamp when recent migration starts (ms) */
int64_t start_time;
/* Total time used by latest migration (ms) */
int64_t total_time;
/* Timestamp when VM is down (ms) to migrate the last stuff */
int64_t downtime_start;
int64_t downtime;
int64_t expected_downtime;
bool enabled_capabilities[MIGRATION_CAPABILITY__MAX];
int64_t setup_time;
/*
* Whether guest was running when we enter the completion stage.
* If migration is interrupted by any reason, we need to continue
* running the guest on source.
*/
bool vm_was_running;
/* Flag set once the migration has been asked to enter postcopy */
bool start_postcopy;
/* Flag set after postcopy has sent the device state */
bool postcopy_after_devices;
/* Flag set once the migration thread is running (and needs joining) */
bool migration_thread_running;
/* Flag set once the migration thread called bdrv_inactivate_all */
bool block_inactive;
/* Migration is paused due to pause-before-switchover */
QemuSemaphore pause_sem;
/* The semaphore is used to notify COLO thread that failover is finished */
QemuSemaphore colo_exit_sem;
/* The semaphore is used to notify COLO thread to do checkpoint */
QemuSemaphore colo_checkpoint_sem;
int64_t colo_checkpoint_time;
QEMUTimer *colo_delay_timer;
/* The first error that has occurred.
We used the mutex to be able to return the 1st error message */
Error *error;
/* mutex to protect errp */
QemuMutex error_mutex;
/* Do we have to clean up -b/-i from old migrate parameters */
/* This feature is deprecated and will be removed */
bool must_remove_block_options;
/*
* Global switch on whether we need to store the global state
* during migration.
*/
bool store_global_state;
/* Whether the VM is only allowing for migratable devices */
bool only_migratable;
/* Whether we send QEMU_VM_CONFIGURATION during migration */
bool send_configuration;
/* Whether we send section footer during migration */
bool send_section_footer;
/* Needed by postcopy-pause state */
QemuSemaphore postcopy_pause_sem;
QemuSemaphore postcopy_pause_rp_sem;
};
void migrate_set_state(int *state, int old_state, int new_state);
void migration_fd_process_incoming(QEMUFile *f);
void migration_ioc_process_incoming(QIOChannel *ioc);
void migration_incoming_process(void);
bool migration_has_all_channels(void);
uint64_t migrate_max_downtime(void);
void migrate_set_error(MigrationState *s, const Error *error);
void migrate_fd_error(MigrationState *s, const Error *error);
void migrate_fd_connect(MigrationState *s, Error *error_in);
void migrate_init(MigrationState *s);
bool migration_is_blocked(Error **errp);
/* True if outgoing migration has entered postcopy phase */
bool migration_in_postcopy(void);
MigrationState *migrate_get_current(void);
bool migrate_postcopy(void);
bool migrate_release_ram(void);
bool migrate_postcopy_ram(void);
bool migrate_zero_blocks(void);
bool migrate_dirty_bitmaps(void);
bool migrate_auto_converge(void);
bool migrate_use_multifd(void);
bool migrate_pause_before_switchover(void);
int migrate_multifd_channels(void);
int migrate_multifd_page_count(void);
int migrate_use_xbzrle(void);
int64_t migrate_xbzrle_cache_size(void);
bool migrate_colo_enabled(void);
bool migrate_use_block(void);
bool migrate_use_block_incremental(void);
bool migrate_use_return_path(void);
bool migrate_use_compression(void);
int migrate_compress_level(void);
int migrate_compress_threads(void);
int migrate_decompress_threads(void);
bool migrate_use_events(void);
bool migrate_postcopy_blocktime(void);
/* Sending on the return path - generic and then for each message type */
void migrate_send_rp_shut(MigrationIncomingState *mis,
uint32_t value);
void migrate_send_rp_pong(MigrationIncomingState *mis,
uint32_t value);
int migrate_send_rp_req_pages(MigrationIncomingState *mis, const char* rbname,
ram_addr_t start, size_t len);
void migrate_send_rp_recv_bitmap(MigrationIncomingState *mis,
char *block_name);
void migrate_send_rp_resume_ack(MigrationIncomingState *mis, uint32_t value);
void dirty_bitmap_mig_before_vm_start(void);
void init_dirty_bitmap_incoming_migration(void);
#endif
|