aboutsummaryrefslogtreecommitdiff
path: root/drivers/xen/events.c
blob: 347f17edad77bab15f1e5ca286a833a3a8392906 (plain)
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
/*
 * Xen event channels
 *
 * Xen models interrupts with abstract event channels.  Because each
 * domain gets 1024 event channels, but NR_IRQ is not that large, we
 * must dynamically map irqs<->event channels.  The event channels
 * interface with the rest of the kernel by defining a xen interrupt
 * chip.  When an event is recieved, it is mapped to an irq and sent
 * through the normal interrupt processing path.
 *
 * There are four kinds of events which can be mapped to an event
 * channel:
 *
 * 1. Inter-domain notifications.  This includes all the virtual
 *    device events, since they're driven by front-ends in another domain
 *    (typically dom0).
 * 2. VIRQs, typically used for timers.  These are per-cpu events.
 * 3. IPIs.
 * 4. Hardware interrupts. Not supported at present.
 *
 * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
 */

#include <linux/linkage.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/bootmem.h>
#include <linux/slab.h>

#include <asm/desc.h>
#include <asm/ptrace.h>
#include <asm/irq.h>
#include <asm/idle.h>
#include <asm/sync_bitops.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>

#include <xen/xen.h>
#include <xen/hvm.h>
#include <xen/xen-ops.h>
#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/event_channel.h>
#include <xen/interface/hvm/hvm_op.h>
#include <xen/interface/hvm/params.h>

/*
 * This lock protects updates to the following mapping and reference-count
 * arrays. The lock does not need to be acquired to read the mapping tables.
 */
static DEFINE_SPINLOCK(irq_mapping_update_lock);

/* IRQ <-> VIRQ mapping. */
static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};

/* IRQ <-> IPI mapping */
static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};

/* Interrupt types. */
enum xen_irq_type {
	IRQT_UNBOUND = 0,
	IRQT_PIRQ,
	IRQT_VIRQ,
	IRQT_IPI,
	IRQT_EVTCHN
};

/*
 * Packed IRQ information:
 * type - enum xen_irq_type
 * event channel - irq->event channel mapping
 * cpu - cpu this event channel is bound to
 * index - type-specific information:
 *    PIRQ - vector, with MSB being "needs EIO"
 *    VIRQ - virq number
 *    IPI - IPI vector
 *    EVTCHN -
 */
struct irq_info
{
	enum xen_irq_type type;	/* type */
	unsigned short evtchn;	/* event channel */
	unsigned short cpu;	/* cpu bound */

	union {
		unsigned short virq;
		enum ipi_vector ipi;
		struct {
			unsigned short gsi;
			unsigned short vector;
		} pirq;
	} u;
};

static struct irq_info irq_info[NR_IRQS];

static int evtchn_to_irq[NR_EVENT_CHANNELS] = {
	[0 ... NR_EVENT_CHANNELS-1] = -1
};
struct cpu_evtchn_s {
	unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG];
};
static struct cpu_evtchn_s *cpu_evtchn_mask_p;
static inline unsigned long *cpu_evtchn_mask(int cpu)
{
	return cpu_evtchn_mask_p[cpu].bits;
}

/* Xen will never allocate port zero for any purpose. */
#define VALID_EVTCHN(chn)	((chn) != 0)

static struct irq_chip xen_dynamic_chip;
static struct irq_chip xen_percpu_chip;

/* Constructor for packed IRQ information. */
static struct irq_info mk_unbound_info(void)
{
	return (struct irq_info) { .type = IRQT_UNBOUND };
}

static struct irq_info mk_evtchn_info(unsigned short evtchn)
{
	return (struct irq_info) { .type = IRQT_EVTCHN, .evtchn = evtchn,
			.cpu = 0 };
}

static struct irq_info mk_ipi_info(unsigned short evtchn, enum ipi_vector ipi)
{
	return (struct irq_info) { .type = IRQT_IPI, .evtchn = evtchn,
			.cpu = 0, .u.ipi = ipi };
}

static struct irq_info mk_virq_info(unsigned short evtchn, unsigned short virq)
{
	return (struct irq_info) { .type = IRQT_VIRQ, .evtchn = evtchn,
			.cpu = 0, .u.virq = virq };
}

static struct irq_info mk_pirq_info(unsigned short evtchn,
				    unsigned short gsi, unsigned short vector)
{
	return (struct irq_info) { .type = IRQT_PIRQ, .evtchn = evtchn,
			.cpu = 0, .u.pirq = { .gsi = gsi, .vector = vector } };
}

/*
 * Accessors for packed IRQ information.
 */
static struct irq_info *info_for_irq(unsigned irq)
{
	return &irq_info[irq];
}

static unsigned int evtchn_from_irq(unsigned irq)
{
	return info_for_irq(irq)->evtchn;
}

unsigned irq_from_evtchn(unsigned int evtchn)
{
	return evtchn_to_irq[evtchn];
}
EXPORT_SYMBOL_GPL(irq_from_evtchn);

static enum ipi_vector ipi_from_irq(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);

	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_IPI);

	return info->u.ipi;
}

static unsigned virq_from_irq(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);

	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_VIRQ);

	return info->u.virq;
}

static unsigned gsi_from_irq(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);

	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_PIRQ);

	return info->u.pirq.gsi;
}

static unsigned vector_from_irq(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);

	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_PIRQ);

	return info->u.pirq.vector;
}

static enum xen_irq_type type_from_irq(unsigned irq)
{
	return info_for_irq(irq)->type;
}

static unsigned cpu_from_irq(unsigned irq)
{
	return info_for_irq(irq)->cpu;
}

static unsigned int cpu_from_evtchn(unsigned int evtchn)
{
	int irq = evtchn_to_irq[evtchn];
	unsigned ret = 0;

	if (irq != -1)
		ret = cpu_from_irq(irq);

	return ret;
}

static inline unsigned long active_evtchns(unsigned int cpu,
					   struct shared_info *sh,
					   unsigned int idx)
{
	return (sh->evtchn_pending[idx] &
		cpu_evtchn_mask(cpu)[idx] &
		~sh->evtchn_mask[idx]);
}

static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
{
	int irq = evtchn_to_irq[chn];

	BUG_ON(irq == -1);
#ifdef CONFIG_SMP
	cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu));
#endif

	__clear_bit(chn, cpu_evtchn_mask(cpu_from_irq(irq)));
	__set_bit(chn, cpu_evtchn_mask(cpu));

	irq_info[irq].cpu = cpu;
}

static void init_evtchn_cpu_bindings(void)
{
#ifdef CONFIG_SMP
	struct irq_desc *desc;
	int i;

	/* By default all event channels notify CPU#0. */
	for_each_irq_desc(i, desc) {
		cpumask_copy(desc->affinity, cpumask_of(0));
	}
#endif

	memset(cpu_evtchn_mask(0), ~0, sizeof(struct cpu_evtchn_s));
}

static inline void clear_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	sync_clear_bit(port, &s->evtchn_pending[0]);
}

static inline void set_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	sync_set_bit(port, &s->evtchn_pending[0]);
}

static inline int test_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	return sync_test_bit(port, &s->evtchn_pending[0]);
}


/**
 * notify_remote_via_irq - send event to remote end of event channel via irq
 * @irq: irq of event channel to send event to
 *
 * Unlike notify_remote_via_evtchn(), this is safe to use across
 * save/restore. Notifications on a broken connection are silently
 * dropped.
 */
void notify_remote_via_irq(int irq)
{
	int evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		notify_remote_via_evtchn(evtchn);
}
EXPORT_SYMBOL_GPL(notify_remote_via_irq);

static void mask_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	sync_set_bit(port, &s->evtchn_mask[0]);
}

static void unmask_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	unsigned int cpu = get_cpu();

	BUG_ON(!irqs_disabled());

	/* Slow path (hypercall) if this is a non-local port. */
	if (unlikely(cpu != cpu_from_evtchn(port))) {
		struct evtchn_unmask unmask = { .port = port };
		(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
	} else {
		struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu);

		sync_clear_bit(port, &s->evtchn_mask[0]);

		/*
		 * The following is basically the equivalent of
		 * 'hw_resend_irq'. Just like a real IO-APIC we 'lose
		 * the interrupt edge' if the channel is masked.
		 */
		if (sync_test_bit(port, &s->evtchn_pending[0]) &&
		    !sync_test_and_set_bit(port / BITS_PER_LONG,
					   &vcpu_info->evtchn_pending_sel))
			vcpu_info->evtchn_upcall_pending = 1;
	}

	put_cpu();
}

static int find_unbound_irq(void)
{
	struct irq_data *data;
	int irq, res;

	for (irq = 0; irq < nr_irqs; irq++) {
		data = irq_get_irq_data(irq);
		/* only 0->15 have init'd desc; handle irq > 16 */
		if (!data)
			break;
		if (data->chip == &no_irq_chip)
			break;
		if (data->chip != &xen_dynamic_chip)
			continue;
		if (irq_info[irq].type == IRQT_UNBOUND)
			return irq;
	}

	if (irq == nr_irqs)
		panic("No available IRQ to bind to: increase nr_irqs!\n");

	res = irq_alloc_desc_at(irq, 0);

	if (WARN_ON(res != irq))
		return -1;

	return irq;
}

int bind_evtchn_to_irq(unsigned int evtchn)
{
	int irq;

	spin_lock(&irq_mapping_update_lock);

	irq = evtchn_to_irq[evtchn];

	if (irq == -1) {
		irq = find_unbound_irq();

		set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
					      handle_fasteoi_irq, "event");

		evtchn_to_irq[evtchn] = irq;
		irq_info[irq] = mk_evtchn_info(evtchn);
	}

	spin_unlock(&irq_mapping_update_lock);

	return irq;
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);

static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
{
	struct evtchn_bind_ipi bind_ipi;
	int evtchn, irq;

	spin_lock(&irq_mapping_update_lock);

	irq = per_cpu(ipi_to_irq, cpu)[ipi];

	if (irq == -1) {
		irq = find_unbound_irq();
		if (irq < 0)
			goto out;

		set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
					      handle_percpu_irq, "ipi");

		bind_ipi.vcpu = cpu;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
						&bind_ipi) != 0)
			BUG();
		evtchn = bind_ipi.port;

		evtchn_to_irq[evtchn] = irq;
		irq_info[irq] = mk_ipi_info(evtchn, ipi);
		per_cpu(ipi_to_irq, cpu)[ipi] = irq;

		bind_evtchn_to_cpu(evtchn, cpu);
	}

 out:
	spin_unlock(&irq_mapping_update_lock);
	return irq;
}


static int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
{
	struct evtchn_bind_virq bind_virq;
	int evtchn, irq;

	spin_lock(&irq_mapping_update_lock);

	irq = per_cpu(virq_to_irq, cpu)[virq];

	if (irq == -1) {
		irq = find_unbound_irq();

		set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
					      handle_percpu_irq, "virq");

		bind_virq.virq = virq;
		bind_virq.vcpu = cpu;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
						&bind_virq) != 0)
			BUG();
		evtchn = bind_virq.port;

		evtchn_to_irq[evtchn] = irq;
		irq_info[irq] = mk_virq_info(evtchn, virq);

		per_cpu(virq_to_irq, cpu)[virq] = irq;

		bind_evtchn_to_cpu(evtchn, cpu);
	}

	spin_unlock(&irq_mapping_update_lock);

	return irq;
}

static void unbind_from_irq(unsigned int irq)
{
	struct evtchn_close close;
	int evtchn = evtchn_from_irq(irq);

	spin_lock(&irq_mapping_update_lock);

	if (VALID_EVTCHN(evtchn)) {
		close.port = evtchn;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
			BUG();

		switch (type_from_irq(irq)) {
		case IRQT_VIRQ:
			per_cpu(virq_to_irq, cpu_from_evtchn(evtchn))
				[virq_from_irq(irq)] = -1;
			break;
		case IRQT_IPI:
			per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn))
				[ipi_from_irq(irq)] = -1;
			break;
		default:
			break;
		}

		/* Closed ports are implicitly re-bound to VCPU0. */
		bind_evtchn_to_cpu(evtchn, 0);

		evtchn_to_irq[evtchn] = -1;
	}

	if (irq_info[irq].type != IRQT_UNBOUND) {
		irq_info[irq] = mk_unbound_info();

		irq_free_desc(irq);
	}

	spin_unlock(&irq_mapping_update_lock);
}

int bind_evtchn_to_irqhandler(unsigned int evtchn,
			      irq_handler_t handler,
			      unsigned long irqflags,
			      const char *devname, void *dev_id)
{
	unsigned int irq;
	int retval;

	irq = bind_evtchn_to_irq(evtchn);
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);

int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
			    irq_handler_t handler,
			    unsigned long irqflags, const char *devname, void *dev_id)
{
	unsigned int irq;
	int retval;

	irq = bind_virq_to_irq(virq, cpu);
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}
EXPORT_SYMBOL_GPL(bind_virq_to_irqhandler);

int bind_ipi_to_irqhandler(enum ipi_vector ipi,
			   unsigned int cpu,
			   irq_handler_t handler,
			   unsigned long irqflags,
			   const char *devname,
			   void *dev_id)
{
	int irq, retval;

	irq = bind_ipi_to_irq(ipi, cpu);
	if (irq < 0)
		return irq;

	irqflags |= IRQF_NO_SUSPEND;
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}

void unbind_from_irqhandler(unsigned int irq, void *dev_id)
{
	free_irq(irq, dev_id);
	unbind_from_irq(irq);
}
EXPORT_SYMBOL_GPL(unbind_from_irqhandler);

void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
{
	int irq = per_cpu(ipi_to_irq, cpu)[vector];
	BUG_ON(irq < 0);
	notify_remote_via_irq(irq);
}

irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
{
	struct shared_info *sh = HYPERVISOR_shared_info;
	int cpu = smp_processor_id();
	unsigned long *cpu_evtchn = cpu_evtchn_mask(cpu);
	int i;
	unsigned long flags;
	static DEFINE_SPINLOCK(debug_lock);
	struct vcpu_info *v;

	spin_lock_irqsave(&debug_lock, flags);

	printk("\nvcpu %d\n  ", cpu);

	for_each_online_cpu(i) {
		int pending;
		v = per_cpu(xen_vcpu, i);
		pending = (get_irq_regs() && i == cpu)
			? xen_irqs_disabled(get_irq_regs())
			: v->evtchn_upcall_mask;
		printk("%d: masked=%d pending=%d event_sel %0*lx\n  ", i,
		       pending, v->evtchn_upcall_pending,
		       (int)(sizeof(v->evtchn_pending_sel)*2),
		       v->evtchn_pending_sel);
	}
	v = per_cpu(xen_vcpu, cpu);

	printk("\npending:\n   ");
	for (i = ARRAY_SIZE(sh->evtchn_pending)-1; i >= 0; i--)
		printk("%0*lx%s", (int)sizeof(sh->evtchn_pending[0])*2,
		       sh->evtchn_pending[i],
		       i % 8 == 0 ? "\n   " : " ");
	printk("\nglobal mask:\n   ");
	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
		printk("%0*lx%s",
		       (int)(sizeof(sh->evtchn_mask[0])*2),
		       sh->evtchn_mask[i],
		       i % 8 == 0 ? "\n   " : " ");

	printk("\nglobally unmasked:\n   ");
	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
		printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
		       sh->evtchn_pending[i] & ~sh->evtchn_mask[i],
		       i % 8 == 0 ? "\n   " : " ");

	printk("\nlocal cpu%d mask:\n   ", cpu);
	for (i = (NR_EVENT_CHANNELS/BITS_PER_LONG)-1; i >= 0; i--)
		printk("%0*lx%s", (int)(sizeof(cpu_evtchn[0])*2),
		       cpu_evtchn[i],
		       i % 8 == 0 ? "\n   " : " ");

	printk("\nlocally unmasked:\n   ");
	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) {
		unsigned long pending = sh->evtchn_pending[i]
			& ~sh->evtchn_mask[i]
			& cpu_evtchn[i];
		printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
		       pending, i % 8 == 0 ? "\n   " : " ");
	}

	printk("\npending list:\n");
	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
		if (sync_test_bit(i, sh->evtchn_pending)) {
			int word_idx = i / BITS_PER_LONG;
			printk("  %d: event %d -> irq %d%s%s%s\n",
			       cpu_from_evtchn(i), i,
			       evtchn_to_irq[i],
			       sync_test_bit(word_idx, &v->evtchn_pending_sel)
					     ? "" : " l2-clear",
			       !sync_test_bit(i, sh->evtchn_mask)
					     ? "" : " globally-masked",
			       sync_test_bit(i, cpu_evtchn)
					     ? "" : " locally-masked");
		}
	}

	spin_unlock_irqrestore(&debug_lock, flags);

	return IRQ_HANDLED;
}

static DEFINE_PER_CPU(unsigned, xed_nesting_count);

/*
 * Search the CPUs pending events bitmasks.  For each one found, map
 * the event number to an irq, and feed it into do_IRQ() for
 * handling.
 *
 * Xen uses a two-level bitmap to speed searching.  The first level is
 * a bitset of words which contain pending event bits.  The second
 * level is a bitset of pending events themselves.
 */
static void __xen_evtchn_do_upcall(void)
{
	int cpu = get_cpu();
	struct shared_info *s = HYPERVISOR_shared_info;
	struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu);
 	unsigned count;

	do {
		unsigned long pending_words;

		vcpu_info->evtchn_upcall_pending = 0;

		if (__get_cpu_var(xed_nesting_count)++)
			goto out;

#ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a barrier on x86. */
		/* Clear master flag /before/ clearing selector flag. */
		wmb();
#endif
		pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
		while (pending_words != 0) {
			unsigned long pending_bits;
			int word_idx = __ffs(pending_words);
			pending_words &= ~(1UL << word_idx);

			while ((pending_bits = active_evtchns(cpu, s, word_idx)) != 0) {
				int bit_idx = __ffs(pending_bits);
				int port = (word_idx * BITS_PER_LONG) + bit_idx;
				int irq = evtchn_to_irq[port];
				struct irq_desc *desc;

				mask_evtchn(port);
				clear_evtchn(port);

				if (irq != -1) {
					desc = irq_to_desc(irq);
					if (desc)
						generic_handle_irq_desc(irq, desc);
				}
			}
		}

		BUG_ON(!irqs_disabled());

		count = __get_cpu_var(xed_nesting_count);
		__get_cpu_var(xed_nesting_count) = 0;
	} while (count != 1 || vcpu_info->evtchn_upcall_pending);

out:

	put_cpu();
}

void xen_evtchn_do_upcall(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	exit_idle();
	irq_enter();

	__xen_evtchn_do_upcall();

	irq_exit();
	set_irq_regs(old_regs);
}

void xen_hvm_evtchn_do_upcall(void)
{
	__xen_evtchn_do_upcall();
}
EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall);

/* Rebind a new event channel to an existing irq. */
void rebind_evtchn_irq(int evtchn, int irq)
{
	struct irq_info *info = info_for_irq(irq);

	/* Make sure the irq is masked, since the new event channel
	   will also be masked. */
	disable_irq(irq);

	spin_lock(&irq_mapping_update_lock);

	/* After resume the irq<->evtchn mappings are all cleared out */
	BUG_ON(evtchn_to_irq[evtchn] != -1);
	/* Expect irq to have been bound before,
	   so there should be a proper type */
	BUG_ON(info->type == IRQT_UNBOUND);

	evtchn_to_irq[evtchn] = irq;
	irq_info[irq] = mk_evtchn_info(evtchn);

	spin_unlock(&irq_mapping_update_lock);

	/* new event channels are always bound to cpu 0 */
	irq_set_affinity(irq, cpumask_of(0));

	/* Unmask the event channel. */
	enable_irq(irq);
}

/* Rebind an evtchn so that it gets delivered to a specific cpu */
static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
{
	struct evtchn_bind_vcpu bind_vcpu;
	int evtchn = evtchn_from_irq(irq);

	/* events delivered via platform PCI interrupts are always
	 * routed to vcpu 0 */
	if (!VALID_EVTCHN(evtchn) ||
		(xen_hvm_domain() && !xen_have_vector_callback))
		return -1;

	/* Send future instances of this interrupt to other vcpu. */
	bind_vcpu.port = evtchn;
	bind_vcpu.vcpu = tcpu;

	/*
	 * If this fails, it usually just indicates that we're dealing with a
	 * virq or IPI channel, which don't actually need to be rebound. Ignore
	 * it, but don't do the xenlinux-level rebind in that case.
	 */
	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
		bind_evtchn_to_cpu(evtchn, tcpu);

	return 0;
}

static int set_affinity_irq(unsigned irq, const struct cpumask *dest)
{
	unsigned tcpu = cpumask_first(dest);

	return rebind_irq_to_cpu(irq, tcpu);
}

int resend_irq_on_evtchn(unsigned int irq)
{
	int masked, evtchn = evtchn_from_irq(irq);
	struct shared_info *s = HYPERVISOR_shared_info;

	if (!VALID_EVTCHN(evtchn))
		return 1;

	masked = sync_test_and_set_bit(evtchn, s->evtchn_mask);
	sync_set_bit(evtchn, s->evtchn_pending);
	if (!masked)
		unmask_evtchn(evtchn);

	return 1;
}

static void enable_dynirq(unsigned int irq)
{
	int evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		unmask_evtchn(evtchn);
}

static void disable_dynirq(unsigned int irq)
{
	int evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		mask_evtchn(evtchn);
}

static void ack_dynirq(unsigned int irq)
{
	int evtchn = evtchn_from_irq(irq);

	move_masked_irq(irq);

	if (VALID_EVTCHN(evtchn))
		unmask_evtchn(evtchn);
}

static int retrigger_dynirq(unsigned int irq)
{
	int evtchn = evtchn_from_irq(irq);
	struct shared_info *sh = HYPERVISOR_shared_info;
	int ret = 0;

	if (VALID_EVTCHN(evtchn)) {
		int masked;

		masked = sync_test_and_set_bit(evtchn, sh->evtchn_mask);
		sync_set_bit(evtchn, sh->evtchn_pending);
		if (!masked)
			unmask_evtchn(evtchn);
		ret = 1;
	}

	return ret;
}

static void restore_cpu_virqs(unsigned int cpu)
{
	struct evtchn_bind_virq bind_virq;
	int virq, irq, evtchn;

	for (virq = 0; virq < NR_VIRQS; virq++) {
		if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1)
			continue;

		BUG_ON(virq_from_irq(irq) != virq);

		/* Get a new binding from Xen. */
		bind_virq.virq = virq;
		bind_virq.vcpu = cpu;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
						&bind_virq) != 0)
			BUG();
		evtchn = bind_virq.port;

		/* Record the new mapping. */
		evtchn_to_irq[evtchn] = irq;
		irq_info[irq] = mk_virq_info(evtchn, virq);
		bind_evtchn_to_cpu(evtchn, cpu);

		/* Ready for use. */
		unmask_evtchn(evtchn);
	}
}

static void restore_cpu_ipis(unsigned int cpu)
{
	struct evtchn_bind_ipi bind_ipi;
	int ipi, irq, evtchn;

	for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) {
		if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1)
			continue;

		BUG_ON(ipi_from_irq(irq) != ipi);

		/* Get a new binding from Xen. */
		bind_ipi.vcpu = cpu;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
						&bind_ipi) != 0)
			BUG();
		evtchn = bind_ipi.port;

		/* Record the new mapping. */
		evtchn_to_irq[evtchn] = irq;
		irq_info[irq] = mk_ipi_info(evtchn, ipi);
		bind_evtchn_to_cpu(evtchn, cpu);

		/* Ready for use. */
		unmask_evtchn(evtchn);

	}
}

/* Clear an irq's pending state, in preparation for polling on it */
void xen_clear_irq_pending(int irq)
{
	int evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		clear_evtchn(evtchn);
}

void xen_set_irq_pending(int irq)
{
	int evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		set_evtchn(evtchn);
}

bool xen_test_irq_pending(int irq)
{
	int evtchn = evtchn_from_irq(irq);
	bool ret = false;

	if (VALID_EVTCHN(evtchn))
		ret = test_evtchn(evtchn);

	return ret;
}

/* Poll waiting for an irq to become pending.  In the usual case, the
   irq will be disabled so it won't deliver an interrupt. */
void xen_poll_irq(int irq)
{
	evtchn_port_t evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn)) {
		struct sched_poll poll;

		poll.nr_ports = 1;
		poll.timeout = 0;
		set_xen_guest_handle(poll.ports, &evtchn);

		if (HYPERVISOR_sched_op(SCHEDOP_poll, &poll) != 0)
			BUG();
	}
}

void xen_irq_resume(void)
{
	unsigned int cpu, irq, evtchn;

	init_evtchn_cpu_bindings();

	/* New event-channel space is not 'live' yet. */
	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
		mask_evtchn(evtchn);

	/* No IRQ <-> event-channel mappings. */
	for (irq = 0; irq < nr_irqs; irq++)
		irq_info[irq].evtchn = 0; /* zap event-channel binding */

	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
		evtchn_to_irq[evtchn] = -1;

	for_each_possible_cpu(cpu) {
		restore_cpu_virqs(cpu);
		restore_cpu_ipis(cpu);
	}
}

static struct irq_chip xen_dynamic_chip __read_mostly = {
	.name		= "xen-dyn",

	.disable	= disable_dynirq,
	.mask		= disable_dynirq,
	.unmask		= enable_dynirq,

	.eoi		= ack_dynirq,
	.set_affinity	= set_affinity_irq,
	.retrigger	= retrigger_dynirq,
};

static struct irq_chip xen_percpu_chip __read_mostly = {
	.name		= "xen-percpu",

	.disable	= disable_dynirq,
	.mask		= disable_dynirq,
	.unmask		= enable_dynirq,

	.ack		= ack_dynirq,
};

int xen_set_callback_via(uint64_t via)
{
	struct xen_hvm_param a;
	a.domid = DOMID_SELF;
	a.index = HVM_PARAM_CALLBACK_IRQ;
	a.value = via;
	return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
}
EXPORT_SYMBOL_GPL(xen_set_callback_via);

#ifdef CONFIG_XEN_PVHVM
/* Vector callbacks are better than PCI interrupts to receive event
 * channel notifications because we can receive vector callbacks on any
 * vcpu and we don't need PCI support or APIC interactions. */
void xen_callback_vector(void)
{
	int rc;
	uint64_t callback_via;
	if (xen_have_vector_callback) {
		callback_via = HVM_CALLBACK_VECTOR(XEN_HVM_EVTCHN_CALLBACK);
		rc = xen_set_callback_via(callback_via);
		if (rc) {
			printk(KERN_ERR "Request for Xen HVM callback vector"
					" failed.\n");
			xen_have_vector_callback = 0;
			return;
		}
		printk(KERN_INFO "Xen HVM callback vector for event delivery is "
				"enabled\n");
		/* in the restore case the vector has already been allocated */
		if (!test_bit(XEN_HVM_EVTCHN_CALLBACK, used_vectors))
			alloc_intr_gate(XEN_HVM_EVTCHN_CALLBACK, xen_hvm_callback_vector);
	}
}
#else
void xen_callback_vector(void) {}
#endif

void __init xen_init_IRQ(void)
{
	int i;

	cpu_evtchn_mask_p = kcalloc(nr_cpu_ids, sizeof(struct cpu_evtchn_s),
				    GFP_KERNEL);
	BUG_ON(cpu_evtchn_mask_p == NULL);

	init_evtchn_cpu_bindings();

	/* No event channels are 'live' right now. */
	for (i = 0; i < NR_EVENT_CHANNELS; i++)
		mask_evtchn(i);

	if (xen_hvm_domain()) {
		xen_callback_vector();
		native_init_IRQ();
	} else {
		irq_ctx_init(smp_processor_id());
	}
}