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
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
|
/****************************************************************************
* (C) 2009 - George Dunlap - Citrix Systems R&D UK, Ltd
****************************************************************************
*
* File: common/csched_credit2.c
* Author: George Dunlap
*
* Description: Credit-based SMP CPU scheduler
* Based on an earlier verson by Emmanuel Ackaouy.
*/
#include <xen/config.h>
#include <xen/init.h>
#include <xen/lib.h>
#include <xen/sched.h>
#include <xen/domain.h>
#include <xen/delay.h>
#include <xen/event.h>
#include <xen/time.h>
#include <xen/perfc.h>
#include <xen/sched-if.h>
#include <xen/softirq.h>
#include <asm/atomic.h>
#include <xen/errno.h>
#include <xen/trace.h>
#if __i386__
#define PRI_stime "lld"
#else
#define PRI_stime "ld"
#endif
#define d2printk(x...)
//#define d2printk printk
#define TRC_CSCHED2_TICK TRC_SCHED_CLASS + 1
#define TRC_CSCHED2_RUNQ_POS TRC_SCHED_CLASS + 2
#define TRC_CSCHED2_CREDIT_BURN TRC_SCHED_CLASS + 3
#define TRC_CSCHED2_CREDIT_ADD TRC_SCHED_CLASS + 4
#define TRC_CSCHED2_TICKLE_CHECK TRC_SCHED_CLASS + 5
#define TRC_CSCHED2_TICKLE TRC_SCHED_CLASS + 6
#define TRC_CSCHED2_CREDIT_RESET TRC_SCHED_CLASS + 7
#define TRC_CSCHED2_SCHED_TASKLET TRC_SCHED_CLASS + 8
/*
* WARNING: This is still in an experimental phase. Status and work can be found at the
* credit2 wiki page:
* http://wiki.xensource.com/xenwiki/Credit2_Scheduler_Development
* TODO:
* + Immediate bug-fixes
* - Do per-runqueue, grab proper lock for dump debugkey
* + Multiple sockets
* - Detect cpu layout and make runqueue map, one per L2 (make_runq_map())
* - Simple load balancer / runqueue assignment
* - Runqueue load measurement
* - Load-based load balancer
* + Hyperthreading
* - Look for non-busy core if possible
* - "Discount" time run on a thread with busy siblings
* + Algorithm:
* - "Mixed work" problem: if a VM is playing audio (5%) but also burning cpu (e.g.,
* a flash animation in the background) can we schedule it with low enough latency
* so that audio doesn't skip?
* - Cap and reservation: How to implement with the current system?
* + Optimizing
* - Profiling, making new algorithms, making math more efficient (no long division)
*/
/*
* Design:
*
* VMs "burn" credits based on their weight; higher weight means
* credits burn more slowly. The highest weight vcpu burns credits at
* a rate of 1 credit per nanosecond. Others burn proportionally
* more.
*
* vcpus are inserted into the runqueue by credit order.
*
* Credits are "reset" when the next vcpu in the runqueue is less than
* or equal to zero. At that point, everyone's credits are "clipped"
* to a small value, and a fixed credit is added to everyone.
*
* The plan is for all cores that share an L2 will share the same
* runqueue. At the moment, there is one global runqueue for all
* cores.
*/
/*
* Locking:
* - Schedule-lock is per-runqueue
* + Protects runqueue data, runqueue insertion, &c
* + Also protects updates to private sched vcpu structure
* + Must be grabbed using vcpu_schedule_lock_irq() to make sure vcpu->processr
* doesn't change under our feet.
* - Private data lock
* + Protects access to global domain list
* + All other private data is written at init and only read afterwards.
* Ordering:
* - We grab private->schedule when updating domain weight; so we
* must never grab private if a schedule lock is held.
*/
/*
* Basic constants
*/
/* Default weight: How much a new domain starts with */
#define CSCHED_DEFAULT_WEIGHT 256
/* Min timer: Minimum length a timer will be set, to
* achieve efficiency */
#define CSCHED_MIN_TIMER MICROSECS(500)
/* Amount of credit VMs begin with, and are reset to.
* ATM, set so that highest-weight VMs can only run for 10ms
* before a reset event. */
#define CSCHED_CREDIT_INIT MILLISECS(10)
/* Carryover: How much "extra" credit may be carried over after
* a reset. */
#define CSCHED_CARRYOVER_MAX CSCHED_MIN_TIMER
/* Reset: Value below which credit will be reset. */
#define CSCHED_CREDIT_RESET 0
/* Max timer: Maximum time a guest can be run for. */
#define CSCHED_MAX_TIMER MILLISECS(2)
#define CSCHED_IDLE_CREDIT (-(1<<30))
/*
* Flags
*/
/* CSFLAG_scheduled: Is this vcpu either running on, or context-switching off,
* a physical cpu?
* + Accessed only with runqueue lock held
* + Set when chosen as next in csched_schedule().
* + Cleared after context switch has been saved in csched_context_saved()
* + Checked in vcpu_wake to see if we can add to the runqueue, or if we should
* set CSFLAG_delayed_runq_add
* + Checked to be false in runq_insert.
*/
#define __CSFLAG_scheduled 1
#define CSFLAG_scheduled (1<<__CSFLAG_scheduled)
/* CSFLAG_delayed_runq_add: Do we need to add this to the runqueue once it'd done
* being context switched out?
* + Set when scheduling out in csched_schedule() if prev is runnable
* + Set in csched_vcpu_wake if it finds CSFLAG_scheduled set
* + Read in csched_context_saved(). If set, it adds prev to the runqueue and
* clears the bit.
*/
#define __CSFLAG_delayed_runq_add 2
#define CSFLAG_delayed_runq_add (1<<__CSFLAG_delayed_runq_add)
/*
* Useful macros
*/
#define CSCHED_PRIV(_ops) \
((struct csched_private *)((_ops)->sched_data))
#define CSCHED_VCPU(_vcpu) ((struct csched_vcpu *) (_vcpu)->sched_priv)
#define CSCHED_DOM(_dom) ((struct csched_dom *) (_dom)->sched_priv)
#define CSCHED_CPUONLINE(_pool) \
(((_pool) == NULL) ? &cpupool_free_cpus : &(_pool)->cpu_valid)
/* CPU to runq_id macro */
#define c2r(_ops, _cpu) (CSCHED_PRIV(_ops)->runq_map[(_cpu)])
/* CPU to runqueue struct macro */
#define RQD(_ops, _cpu) (&CSCHED_PRIV(_ops)->rqd[c2r(_ops, _cpu)])
/*
* Per-runqueue data
*/
struct csched_runqueue_data {
int id;
struct list_head runq; /* Ordered list of runnable vms */
struct list_head svc; /* List of all vcpus assigned to this runqueue */
int max_weight;
int cpu_min, cpu_max; /* Range of physical cpus this runqueue runs */
cpumask_t idle, /* Currently idle */
tickled; /* Another cpu in the queue is already targeted for this one */
};
/*
* System-wide private data
*/
struct csched_private {
spinlock_t lock;
uint32_t ncpus;
struct list_head sdom; /* Used mostly for dump keyhandler. */
int runq_map[NR_CPUS];
uint32_t runq_count;
struct csched_runqueue_data rqd[NR_CPUS];
};
/*
* Virtual CPU
*/
struct csched_vcpu {
struct list_head rqd_elem; /* On the runqueue data list */
struct list_head sdom_elem; /* On the domain vcpu list */
struct list_head runq_elem; /* On the runqueue */
/* Up-pointers */
struct csched_dom *sdom;
struct vcpu *vcpu;
int weight;
int credit;
s_time_t start_time; /* When we were scheduled (used for credit) */
unsigned flags; /* 16 bits doesn't seem to play well with clear_bit() */
};
/*
* Domain
*/
struct csched_dom {
struct list_head vcpu;
struct list_head sdom_elem;
struct domain *dom;
uint16_t weight;
uint16_t nr_vcpus;
};
/*
* Time-to-credit, credit-to-time.
* FIXME: Do pre-calculated division?
*/
static s_time_t t2c(struct csched_runqueue_data *rqd, s_time_t time, struct csched_vcpu *svc)
{
return time * rqd->max_weight / svc->weight;
}
static s_time_t c2t(struct csched_runqueue_data *rqd, s_time_t credit, struct csched_vcpu *svc)
{
return credit * svc->weight / rqd->max_weight;
}
/*
* Runqueue related code
*/
static /*inline*/ int
__vcpu_on_runq(struct csched_vcpu *svc)
{
return !list_empty(&svc->runq_elem);
}
static /*inline*/ struct csched_vcpu *
__runq_elem(struct list_head *elem)
{
return list_entry(elem, struct csched_vcpu, runq_elem);
}
static int
__runq_insert(struct list_head *runq, struct csched_vcpu *svc)
{
struct list_head *iter;
int pos = 0;
d2printk("rqi d%dv%d\n",
svc->vcpu->domain->domain_id,
svc->vcpu->vcpu_id);
/* Idle vcpus not allowed on the runqueue anymore */
BUG_ON(is_idle_vcpu(svc->vcpu));
BUG_ON(svc->vcpu->is_running);
BUG_ON(test_bit(__CSFLAG_scheduled, &svc->flags));
list_for_each( iter, runq )
{
struct csched_vcpu * iter_svc = __runq_elem(iter);
if ( svc->credit > iter_svc->credit )
{
d2printk(" p%d d%dv%d\n",
pos,
iter_svc->vcpu->domain->domain_id,
iter_svc->vcpu->vcpu_id);
break;
}
pos++;
}
list_add_tail(&svc->runq_elem, iter);
return pos;
}
static void
runq_insert(const struct scheduler *ops, unsigned int cpu, struct csched_vcpu *svc)
{
struct list_head * runq = &RQD(ops, cpu)->runq;
int pos = 0;
ASSERT( spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock) );
BUG_ON( __vcpu_on_runq(svc) );
BUG_ON( c2r(ops, cpu) != c2r(ops, svc->vcpu->processor) );
pos = __runq_insert(runq, svc);
{
struct {
unsigned dom:16,vcpu:16;
unsigned pos;
} d;
d.dom = svc->vcpu->domain->domain_id;
d.vcpu = svc->vcpu->vcpu_id;
d.pos = pos;
trace_var(TRC_CSCHED2_RUNQ_POS, 0,
sizeof(d),
(unsigned char *)&d);
}
return;
}
static inline void
__runq_remove(struct csched_vcpu *svc)
{
BUG_ON( !__vcpu_on_runq(svc) );
list_del_init(&svc->runq_elem);
}
void burn_credits(struct csched_runqueue_data *rqd, struct csched_vcpu *, s_time_t);
/* Check to see if the item on the runqueue is higher priority than what's
* currently running; if so, wake up the processor */
static /*inline*/ void
runq_tickle(const struct scheduler *ops, unsigned int cpu, struct csched_vcpu *new, s_time_t now)
{
int i, ipid=-1;
s_time_t lowest=(1<<30);
struct csched_runqueue_data *rqd = RQD(ops, cpu);
cpumask_t *online, mask;
d2printk("rqt d%dv%d cd%dv%d\n",
new->vcpu->domain->domain_id,
new->vcpu->vcpu_id,
current->domain->domain_id,
current->vcpu_id);
online = CSCHED_CPUONLINE(per_cpu(cpupool, cpu));
/* Get a mask of idle, but not tickled */
cpus_andnot(mask, rqd->idle, rqd->tickled);
/* If it's not empty, choose one */
if ( !cpus_empty(mask) )
{
ipid=first_cpu(mask);
goto tickle;
}
/* Otherwise, look for the non-idle cpu with the lowest credit,
* skipping cpus which have been tickled but not scheduled yet */
cpus_andnot(mask, *online, rqd->idle);
cpus_andnot(mask, mask, rqd->tickled);
for_each_cpu_mask(i, mask)
{
struct csched_vcpu * cur;
cur = CSCHED_VCPU(per_cpu(schedule_data, i).curr);
BUG_ON(is_idle_vcpu(cur->vcpu));
/* Update credits for current to see if we want to preempt */
burn_credits(rqd, cur, now);
if ( cur->credit < lowest )
{
ipid = i;
lowest = cur->credit;
}
/* TRACE */ {
struct {
unsigned dom:16,vcpu:16;
unsigned credit;
} d;
d.dom = cur->vcpu->domain->domain_id;
d.vcpu = cur->vcpu->vcpu_id;
d.credit = cur->credit;
trace_var(TRC_CSCHED2_TICKLE_CHECK, 0,
sizeof(d),
(unsigned char *)&d);
}
}
/* At this point, if ipid is non-zero, see if the lowest is lower than new */
if ( ipid == -1 || lowest > new->credit )
goto no_tickle;
tickle:
BUG_ON(ipid == -1);
/* TRACE */ {
struct {
unsigned cpu:8;
} d;
d.cpu = ipid;
trace_var(TRC_CSCHED2_TICKLE, 0,
sizeof(d),
(unsigned char *)&d);
}
cpu_set(ipid, rqd->tickled);
cpu_raise_softirq(ipid, SCHEDULE_SOFTIRQ);
no_tickle:
return;
}
/*
* Credit-related code
*/
static void reset_credit(const struct scheduler *ops, int cpu, s_time_t now)
{
struct list_head *iter;
list_for_each( iter, &RQD(ops, cpu)->svc )
{
struct csched_vcpu * svc = list_entry(iter, struct csched_vcpu, rqd_elem);
int start_credit;
BUG_ON( is_idle_vcpu(svc->vcpu) );
start_credit = svc->credit;
/* "Clip" credits to max carryover */
if ( svc->credit > CSCHED_CARRYOVER_MAX )
svc->credit = CSCHED_CARRYOVER_MAX;
/* And add INIT */
svc->credit += CSCHED_CREDIT_INIT;
svc->start_time = now;
/* TRACE */ {
struct {
unsigned dom:16,vcpu:16;
unsigned credit_start, credit_end;
} d;
d.dom = svc->vcpu->domain->domain_id;
d.vcpu = svc->vcpu->vcpu_id;
d.credit_start = start_credit;
d.credit_end = svc->credit;
trace_var(TRC_CSCHED2_CREDIT_RESET, 0,
sizeof(d),
(unsigned char *)&d);
}
}
/* No need to resort runqueue, as everyone's order should be the same. */
}
void burn_credits(struct csched_runqueue_data *rqd, struct csched_vcpu *svc, s_time_t now)
{
s_time_t delta;
/* Assert svc is current */
ASSERT(svc==CSCHED_VCPU(per_cpu(schedule_data, svc->vcpu->processor).curr));
if ( is_idle_vcpu(svc->vcpu) )
{
BUG_ON(svc->credit != CSCHED_IDLE_CREDIT);
return;
}
delta = now - svc->start_time;
if ( delta > 0 ) {
/* This will round down; should we consider rounding up...? */
svc->credit -= t2c(rqd, delta, svc);
svc->start_time = now;
d2printk("b d%dv%d c%d\n",
svc->vcpu->domain->domain_id,
svc->vcpu->vcpu_id,
svc->credit);
} else {
d2printk("%s: Time went backwards? now %"PRI_stime" start %"PRI_stime"\n",
__func__, now, svc->start_time);
}
/* TRACE */
{
struct {
unsigned dom:16,vcpu:16;
unsigned credit;
int delta;
} d;
d.dom = svc->vcpu->domain->domain_id;
d.vcpu = svc->vcpu->vcpu_id;
d.credit = svc->credit;
d.delta = delta;
trace_var(TRC_CSCHED2_CREDIT_BURN, 0,
sizeof(d),
(unsigned char *)&d);
}
}
/* Find the domain with the highest weight. */
void update_max_weight(struct csched_runqueue_data *rqd, int new_weight, int old_weight)
{
/* Try to avoid brute-force search:
* - If new_weight is larger, max_weigth <- new_weight
* - If old_weight != max_weight, someone else is still max_weight
* (No action required)
* - If old_weight == max_weight, brute-force search for max weight
*/
if ( new_weight > rqd->max_weight )
{
rqd->max_weight = new_weight;
printk("%s: Runqueue id %d max weight %d\n", __func__, rqd->id, rqd->max_weight);
}
else if ( old_weight == rqd->max_weight )
{
struct list_head *iter;
int max_weight = 1;
list_for_each( iter, &rqd->svc )
{
struct csched_vcpu * svc = list_entry(iter, struct csched_vcpu, rqd_elem);
if ( svc->weight > max_weight )
max_weight = svc->weight;
}
rqd->max_weight = max_weight;
printk("%s: Runqueue %d max weight %d\n", __func__, rqd->id, rqd->max_weight);
}
}
#ifndef NDEBUG
static /*inline*/ void
__csched_vcpu_check(struct vcpu *vc)
{
struct csched_vcpu * const svc = CSCHED_VCPU(vc);
struct csched_dom * const sdom = svc->sdom;
BUG_ON( svc->vcpu != vc );
BUG_ON( sdom != CSCHED_DOM(vc->domain) );
if ( sdom )
{
BUG_ON( is_idle_vcpu(vc) );
BUG_ON( sdom->dom != vc->domain );
}
else
{
BUG_ON( !is_idle_vcpu(vc) );
}
}
#define CSCHED_VCPU_CHECK(_vc) (__csched_vcpu_check(_vc))
#else
#define CSCHED_VCPU_CHECK(_vc)
#endif
static void *
csched_alloc_vdata(const struct scheduler *ops, struct vcpu *vc, void *dd)
{
struct csched_vcpu *svc;
/* Allocate per-VCPU info */
svc = xmalloc(struct csched_vcpu);
if ( svc == NULL )
return NULL;
memset(svc, 0, sizeof(*svc));
INIT_LIST_HEAD(&svc->rqd_elem);
INIT_LIST_HEAD(&svc->sdom_elem);
INIT_LIST_HEAD(&svc->runq_elem);
svc->sdom = dd;
svc->vcpu = vc;
svc->flags = 0U;
if ( ! is_idle_vcpu(vc) )
{
BUG_ON( svc->sdom == NULL );
svc->credit = CSCHED_CREDIT_INIT;
svc->weight = svc->sdom->weight;
}
else
{
BUG_ON( svc->sdom != NULL );
svc->credit = CSCHED_IDLE_CREDIT;
svc->weight = 0;
}
return svc;
}
static void
csched_vcpu_insert(const struct scheduler *ops, struct vcpu *vc)
{
struct csched_vcpu *svc = vc->sched_priv;
struct domain * const dom = vc->domain;
struct csched_dom *sdom = CSCHED_DOM(dom);
printk("%s: Inserting d%dv%d\n",
__func__, dom->domain_id, vc->vcpu_id);
if ( ! is_idle_vcpu(vc) )
{
/* FIXME: Do we need the private lock here? */
list_add_tail(&svc->sdom_elem, &svc->sdom->vcpu);
/* Add vcpu to runqueue of initial processor */
/* FIXME: Abstract for multiple runqueues */
vcpu_schedule_lock_irq(vc);
list_add_tail(&svc->rqd_elem, &RQD(ops, vc->processor)->svc);
update_max_weight(RQD(ops, vc->processor), svc->weight, 0);
vcpu_schedule_unlock_irq(vc);
sdom->nr_vcpus++;
}
CSCHED_VCPU_CHECK(vc);
}
static void
csched_free_vdata(const struct scheduler *ops, void *priv)
{
struct csched_vcpu *svc = priv;
xfree(svc);
}
static void
csched_vcpu_remove(const struct scheduler *ops, struct vcpu *vc)
{
struct csched_vcpu * const svc = CSCHED_VCPU(vc);
struct csched_dom * const sdom = svc->sdom;
BUG_ON( sdom == NULL );
BUG_ON( !list_empty(&svc->runq_elem) );
if ( ! is_idle_vcpu(vc) )
{
/* Remove from runqueue */
vcpu_schedule_lock_irq(vc);
list_del_init(&svc->rqd_elem);
update_max_weight(RQD(ops, vc->processor), 0, svc->weight);
vcpu_schedule_unlock_irq(vc);
/* Remove from sdom list. Don't need a lock for this, as it's called
* syncronously when nothing else can happen. */
list_del_init(&svc->sdom_elem);
svc->sdom->nr_vcpus--;
}
}
static void
csched_vcpu_sleep(const struct scheduler *ops, struct vcpu *vc)
{
struct csched_vcpu * const svc = CSCHED_VCPU(vc);
BUG_ON( is_idle_vcpu(vc) );
if ( per_cpu(schedule_data, vc->processor).curr == vc )
cpu_raise_softirq(vc->processor, SCHEDULE_SOFTIRQ);
else if ( __vcpu_on_runq(svc) )
__runq_remove(svc);
}
static void
csched_vcpu_wake(const struct scheduler *ops, struct vcpu *vc)
{
struct csched_vcpu * const svc = CSCHED_VCPU(vc);
const unsigned int cpu = vc->processor;
s_time_t now = 0;
/* Schedule lock should be held at this point. */
d2printk("w d%dv%d\n", vc->domain->domain_id, vc->vcpu_id);
BUG_ON( is_idle_vcpu(vc) );
/* Make sure svc priority mod happens before runq check */
if ( unlikely(per_cpu(schedule_data, cpu).curr == vc) )
{
goto out;
}
if ( unlikely(__vcpu_on_runq(svc)) )
{
/* If we've boosted someone that's already on a runqueue, prioritize
* it and inform the cpu in question. */
goto out;
}
/* If the context hasn't been saved for this vcpu yet, we can't put it on
* another runqueue. Instead, we set a flag so that it will be put on the runqueue
* after the context has been saved. */
if ( unlikely (test_bit(__CSFLAG_scheduled, &svc->flags) ) )
{
set_bit(__CSFLAG_delayed_runq_add, &svc->flags);
goto out;
}
now = NOW();
/* Put the VCPU on the runq */
runq_insert(ops, cpu, svc);
runq_tickle(ops, cpu, svc, now);
out:
d2printk("w-\n");
return;
}
static void
csched_context_saved(const struct scheduler *ops, struct vcpu *vc)
{
struct csched_vcpu * const svc = CSCHED_VCPU(vc);
vcpu_schedule_lock_irq(vc);
/* This vcpu is now eligible to be put on the runqueue again */
clear_bit(__CSFLAG_scheduled, &svc->flags);
/* If someone wants it on the runqueue, put it there. */
/*
* NB: We can get rid of CSFLAG_scheduled by checking for
* vc->is_running and __vcpu_on_runq(svc) here. However,
* since we're accessing the flags cacheline anyway,
* it seems a bit pointless; especially as we have plenty of
* bits free.
*/
if ( test_bit(__CSFLAG_delayed_runq_add, &svc->flags) )
{
const unsigned int cpu = vc->processor;
clear_bit(__CSFLAG_delayed_runq_add, &svc->flags);
BUG_ON(__vcpu_on_runq(svc));
runq_insert(ops, cpu, svc);
runq_tickle(ops, cpu, svc, NOW());
}
vcpu_schedule_unlock_irq(vc);
}
static int
csched_cpu_pick(const struct scheduler *ops, struct vcpu *vc)
{
/* FIXME: Chose a schedule group based on load */
/* FIXME: Migrate the vcpu to the new runqueue list, updating
max_weight for each runqueue */
return 0;
}
static int
csched_dom_cntl(
const struct scheduler *ops,
struct domain *d,
struct xen_domctl_scheduler_op *op)
{
struct csched_dom * const sdom = CSCHED_DOM(d);
struct csched_private *prv = CSCHED_PRIV(ops);
unsigned long flags;
if ( op->cmd == XEN_DOMCTL_SCHEDOP_getinfo )
{
op->u.credit2.weight = sdom->weight;
}
else
{
ASSERT(op->cmd == XEN_DOMCTL_SCHEDOP_putinfo);
if ( op->u.credit2.weight != 0 )
{
struct list_head *iter;
int old_weight;
/* Must hold csched_priv lock to update sdom, runq lock to
* update csvcs. */
spin_lock_irqsave(&prv->lock, flags);
old_weight = sdom->weight;
sdom->weight = op->u.credit2.weight;
/* Update weights for vcpus, and max_weight for runqueues on which they reside */
list_for_each ( iter, &sdom->vcpu )
{
struct csched_vcpu *svc = list_entry(iter, struct csched_vcpu, sdom_elem);
|
