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
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
|
/*
* Background jobs (long-running operations)
*
* Copyright (c) 2011 IBM Corp.
* Copyright (c) 2012, 2018 Red Hat, Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qapi/error.h"
#include "qemu/job.h"
#include "qemu/id.h"
#include "qemu/main-loop.h"
#include "trace-root.h"
static QLIST_HEAD(, Job) jobs = QLIST_HEAD_INITIALIZER(jobs);
/* Job State Transition Table */
bool JobSTT[JOB_STATUS__MAX][JOB_STATUS__MAX] = {
/* U, C, R, P, Y, S, W, D, X, E, N */
/* U: */ [JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0},
/* C: */ [JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1},
/* R: */ [JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0},
/* P: */ [JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0},
/* Y: */ [JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0},
/* S: */ [JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0},
/* W: */ [JOB_STATUS_WAITING] = {0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0},
/* D: */ [JOB_STATUS_PENDING] = {0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0},
/* X: */ [JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0},
/* E: */ [JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1},
/* N: */ [JOB_STATUS_NULL] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
};
bool JobVerbTable[JOB_VERB__MAX][JOB_STATUS__MAX] = {
/* U, C, R, P, Y, S, W, D, X, E, N */
[JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0},
[JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
[JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
[JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
[JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0},
[JOB_VERB_FINALIZE] = {0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0},
[JOB_VERB_DISMISS] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0},
};
/* Right now, this mutex is only needed to synchronize accesses to job->busy
* and job->sleep_timer, such as concurrent calls to job_do_yield and
* job_enter. */
static QemuMutex job_mutex;
static void job_lock(void)
{
qemu_mutex_lock(&job_mutex);
}
static void job_unlock(void)
{
qemu_mutex_unlock(&job_mutex);
}
static void __attribute__((__constructor__)) job_init(void)
{
qemu_mutex_init(&job_mutex);
}
/* TODO Make static once the whole state machine is in job.c */
void job_state_transition(Job *job, JobStatus s1)
{
JobStatus s0 = job->status;
assert(s1 >= 0 && s1 <= JOB_STATUS__MAX);
trace_job_state_transition(job, /* TODO re-enable: job->ret */ 0,
JobSTT[s0][s1] ? "allowed" : "disallowed",
JobStatus_str(s0), JobStatus_str(s1));
assert(JobSTT[s0][s1]);
job->status = s1;
}
int job_apply_verb(Job *job, JobVerb verb, Error **errp)
{
JobStatus s0 = job->status;
assert(verb >= 0 && verb <= JOB_VERB__MAX);
trace_job_apply_verb(job, JobStatus_str(s0), JobVerb_str(verb),
JobVerbTable[verb][s0] ? "allowed" : "prohibited");
if (JobVerbTable[verb][s0]) {
return 0;
}
error_setg(errp, "Job '%s' in state '%s' cannot accept command verb '%s'",
job->id, JobStatus_str(s0), JobVerb_str(verb));
return -EPERM;
}
JobType job_type(const Job *job)
{
return job->driver->job_type;
}
const char *job_type_str(const Job *job)
{
return JobType_str(job_type(job));
}
bool job_is_cancelled(Job *job)
{
return job->cancelled;
}
bool job_is_completed(Job *job)
{
switch (job->status) {
case JOB_STATUS_UNDEFINED:
case JOB_STATUS_CREATED:
case JOB_STATUS_RUNNING:
case JOB_STATUS_PAUSED:
case JOB_STATUS_READY:
case JOB_STATUS_STANDBY:
return false;
case JOB_STATUS_WAITING:
case JOB_STATUS_PENDING:
case JOB_STATUS_ABORTING:
case JOB_STATUS_CONCLUDED:
case JOB_STATUS_NULL:
return true;
default:
g_assert_not_reached();
}
return false;
}
bool job_started(Job *job)
{
return job->co;
}
bool job_should_pause(Job *job)
{
return job->pause_count > 0;
}
Job *job_next(Job *job)
{
if (!job) {
return QLIST_FIRST(&jobs);
}
return QLIST_NEXT(job, job_list);
}
Job *job_get(const char *id)
{
Job *job;
QLIST_FOREACH(job, &jobs, job_list) {
if (job->id && !strcmp(id, job->id)) {
return job;
}
}
return NULL;
}
static void job_sleep_timer_cb(void *opaque)
{
Job *job = opaque;
job_enter(job);
}
void *job_create(const char *job_id, const JobDriver *driver, AioContext *ctx,
int flags, Error **errp)
{
Job *job;
if (job_id) {
if (flags & JOB_INTERNAL) {
error_setg(errp, "Cannot specify job ID for internal job");
return NULL;
}
if (!id_wellformed(job_id)) {
error_setg(errp, "Invalid job ID '%s'", job_id);
return NULL;
}
if (job_get(job_id)) {
error_setg(errp, "Job ID '%s' already in use", job_id);
return NULL;
}
} else if (!(flags & JOB_INTERNAL)) {
error_setg(errp, "An explicit job ID is required");
return NULL;
}
job = g_malloc0(driver->instance_size);
job->driver = driver;
job->id = g_strdup(job_id);
job->refcnt = 1;
job->aio_context = ctx;
job->busy = false;
job->paused = true;
job->pause_count = 1;
job->auto_finalize = !(flags & JOB_MANUAL_FINALIZE);
job->auto_dismiss = !(flags & JOB_MANUAL_DISMISS);
job_state_transition(job, JOB_STATUS_CREATED);
aio_timer_init(qemu_get_aio_context(), &job->sleep_timer,
QEMU_CLOCK_REALTIME, SCALE_NS,
job_sleep_timer_cb, job);
QLIST_INSERT_HEAD(&jobs, job, job_list);
return job;
}
void job_ref(Job *job)
{
++job->refcnt;
}
void job_unref(Job *job)
{
if (--job->refcnt == 0) {
assert(job->status == JOB_STATUS_NULL);
assert(!timer_pending(&job->sleep_timer));
if (job->driver->free) {
job->driver->free(job);
}
QLIST_REMOVE(job, job_list);
g_free(job->id);
g_free(job);
}
}
void job_enter_cond(Job *job, bool(*fn)(Job *job))
{
if (!job_started(job)) {
return;
}
if (job->deferred_to_main_loop) {
return;
}
job_lock();
if (job->busy) {
job_unlock();
return;
}
if (fn && !fn(job)) {
job_unlock();
return;
}
assert(!job->deferred_to_main_loop);
timer_del(&job->sleep_timer);
job->busy = true;
job_unlock();
aio_co_wake(job->co);
}
void job_enter(Job *job)
{
job_enter_cond(job, NULL);
}
/* Yield, and schedule a timer to reenter the coroutine after @ns nanoseconds.
* Reentering the job coroutine with block_job_enter() before the timer has
* expired is allowed and cancels the timer.
*
* If @ns is (uint64_t) -1, no timer is scheduled and block_job_enter() must be
* called explicitly. */
void coroutine_fn job_do_yield(Job *job, uint64_t ns)
{
job_lock();
if (ns != -1) {
timer_mod(&job->sleep_timer, ns);
}
job->busy = false;
job_unlock();
qemu_coroutine_yield();
/* Set by job_enter_cond() before re-entering the coroutine. */
assert(job->busy);
}
void coroutine_fn job_pause_point(Job *job)
{
assert(job && job_started(job));
if (!job_should_pause(job)) {
return;
}
if (job_is_cancelled(job)) {
return;
}
if (job->driver->pause) {
job->driver->pause(job);
}
if (job_should_pause(job) && !job_is_cancelled(job)) {
JobStatus status = job->status;
job_state_transition(job, status == JOB_STATUS_READY
? JOB_STATUS_STANDBY
: JOB_STATUS_PAUSED);
job->paused = true;
job_do_yield(job, -1);
job->paused = false;
job_state_transition(job, status);
}
if (job->driver->resume) {
job->driver->resume(job);
}
}
void coroutine_fn job_sleep_ns(Job *job, int64_t ns)
{
assert(job->busy);
/* Check cancellation *before* setting busy = false, too! */
if (job_is_cancelled(job)) {
return;
}
if (!job_should_pause(job)) {
job_do_yield(job, qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + ns);
}
job_pause_point(job);
}
/**
* All jobs must allow a pause point before entering their job proper. This
* ensures that jobs can be paused prior to being started, then resumed later.
*/
static void coroutine_fn job_co_entry(void *opaque)
{
Job *job = opaque;
assert(job && job->driver && job->driver->start);
job_pause_point(job);
job->driver->start(job);
}
void job_start(Job *job)
{
assert(job && !job_started(job) && job->paused &&
job->driver && job->driver->start);
job->co = qemu_coroutine_create(job_co_entry, job);
job->pause_count--;
job->busy = true;
job->paused = false;
job_state_transition(job, JOB_STATUS_RUNNING);
aio_co_enter(job->aio_context, job->co);
}
/* Assumes the block_job_mutex is held */
static bool job_timer_not_pending(Job *job)
{
return !timer_pending(&job->sleep_timer);
}
void job_pause(Job *job)
{
job->pause_count++;
}
void job_resume(Job *job)
{
assert(job->pause_count > 0);
job->pause_count--;
if (job->pause_count) {
return;
}
/* kick only if no timer is pending */
job_enter_cond(job, job_timer_not_pending);
}
void job_user_pause(Job *job, Error **errp)
{
if (job_apply_verb(job, JOB_VERB_PAUSE, errp)) {
return;
}
if (job->user_paused) {
error_setg(errp, "Job is already paused");
return;
}
job->user_paused = true;
job_pause(job);
}
bool job_user_paused(Job *job)
{
return job->user_paused;
}
void job_user_resume(Job *job, Error **errp)
{
assert(job);
if (!job->user_paused || job->pause_count <= 0) {
error_setg(errp, "Can't resume a job that was not paused");
return;
}
if (job_apply_verb(job, JOB_VERB_RESUME, errp)) {
return;
}
if (job->driver->user_resume) {
job->driver->user_resume(job);
}
job->user_paused = false;
job_resume(job);
}
typedef struct {
Job *job;
JobDeferToMainLoopFn *fn;
void *opaque;
} JobDeferToMainLoopData;
static void job_defer_to_main_loop_bh(void *opaque)
{
JobDeferToMainLoopData *data = opaque;
Job *job = data->job;
AioContext *aio_context = job->aio_context;
aio_context_acquire(aio_context);
data->fn(data->job, data->opaque);
aio_context_release(aio_context);
g_free(data);
}
void job_defer_to_main_loop(Job *job, JobDeferToMainLoopFn *fn, void *opaque)
{
JobDeferToMainLoopData *data = g_malloc(sizeof(*data));
data->job = job;
data->fn = fn;
data->opaque = opaque;
job->deferred_to_main_loop = true;
aio_bh_schedule_oneshot(qemu_get_aio_context(),
job_defer_to_main_loop_bh, data);
}
|