summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_xics.c
blob: 7fd247cbd0d11fe2618ee6171af3910c34ccb77c (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
/*
 * Copyright 2012 Michael Ellerman, IBM Corporation.
 * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 */

#include <linux/kernel.h>
#include <linux/kvm_host.h>
#include <linux/err.h>
#include <linux/gfp.h>

#include <asm/uaccess.h>
#include <asm/kvm_book3s.h>
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/xics.h>
#include <asm/debug.h>

#include <linux/debugfs.h>
#include <linux/seq_file.h>

#include "book3s_xics.h"

#if 1
#define XICS_DBG(fmt...) do { } while (0)
#else
#define XICS_DBG(fmt...) trace_printk(fmt)
#endif

#define ENABLE_REALMODE	true
#define DEBUG_REALMODE	false

/*
 * LOCKING
 * =======
 *
 * Each ICS has a mutex protecting the information about the IRQ
 * sources and avoiding simultaneous deliveries if the same interrupt.
 *
 * ICP operations are done via a single compare & swap transaction
 * (most ICP state fits in the union kvmppc_icp_state)
 */

/*
 * TODO
 * ====
 *
 * - To speed up resends, keep a bitmap of "resend" set bits in the
 *   ICS
 *
 * - Speed up server# -> ICP lookup (array ? hash table ?)
 *
 * - Make ICS lockless as well, or at least a per-interrupt lock or hashed
 *   locks array to improve scalability
 *
 * - ioctl's to save/restore the entire state for snapshot & migration
 */

/* -- ICS routines -- */

static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
			    u32 new_irq);

static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level)
{
	struct ics_irq_state *state;
	struct kvmppc_ics *ics;
	u16 src;

	XICS_DBG("ics deliver %#x (level: %d)\n", irq, level);

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics) {
		XICS_DBG("ics_deliver_irq: IRQ 0x%06x not found !\n", irq);
		return -EINVAL;
	}
	state = &ics->irq_state[src];
	if (!state->exists)
		return -EINVAL;

	/*
	 * We set state->asserted locklessly. This should be fine as
	 * we are the only setter, thus concurrent access is undefined
	 * to begin with.
	 */
	if (level == KVM_INTERRUPT_SET_LEVEL)
		state->asserted = 1;
	else if (level == KVM_INTERRUPT_UNSET) {
		state->asserted = 0;
		return 0;
	}

	/* Attempt delivery */
	icp_deliver_irq(xics, NULL, irq);

	return 0;
}

static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
			     struct kvmppc_icp *icp)
{
	int i;

	mutex_lock(&ics->lock);

	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
		struct ics_irq_state *state = &ics->irq_state[i];

		if (!state->resend)
			continue;

		XICS_DBG("resend %#x prio %#x\n", state->number,
			      state->priority);

		mutex_unlock(&ics->lock);
		icp_deliver_irq(xics, icp, state->number);
		mutex_lock(&ics->lock);
	}

	mutex_unlock(&ics->lock);
}

int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priority)
{
	struct kvmppc_xics *xics = kvm->arch.xics;
	struct kvmppc_icp *icp;
	struct kvmppc_ics *ics;
	struct ics_irq_state *state;
	u16 src;
	bool deliver;

	if (!xics)
		return -ENODEV;

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics)
		return -EINVAL;
	state = &ics->irq_state[src];

	icp = kvmppc_xics_find_server(kvm, server);
	if (!icp)
		return -EINVAL;

	mutex_lock(&ics->lock);

	XICS_DBG("set_xive %#x server %#x prio %#x MP:%d RS:%d\n",
		 irq, server, priority,
		 state->masked_pending, state->resend);

	state->server = server;
	state->priority = priority;
	deliver = false;
	if ((state->masked_pending || state->resend) && priority != MASKED) {
		state->masked_pending = 0;
		deliver = true;
	}

	mutex_unlock(&ics->lock);

	if (deliver)
		icp_deliver_irq(xics, icp, irq);

	return 0;
}

int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority)
{
	struct kvmppc_xics *xics = kvm->arch.xics;
	struct kvmppc_ics *ics;
	struct ics_irq_state *state;
	u16 src;

	if (!xics)
		return -ENODEV;

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics)
		return -EINVAL;
	state = &ics->irq_state[src];

	mutex_lock(&ics->lock);
	*server = state->server;
	*priority = state->priority;
	mutex_unlock(&ics->lock);

	return 0;
}

/* -- ICP routines, including hcalls -- */

static inline bool icp_try_update(struct kvmppc_icp *icp,
				  union kvmppc_icp_state old,
				  union kvmppc_icp_state new,
				  bool change_self)
{
	bool success;

	/* Calculate new output value */
	new.out_ee = (new.xisr && (new.pending_pri < new.cppr));

	/* Attempt atomic update */
	success = cmpxchg64(&icp->state.raw, old.raw, new.raw) == old.raw;
	if (!success)
		goto bail;

	XICS_DBG("UPD [%04x] - C:%02x M:%02x PP: %02x PI:%06x R:%d O:%d\n",
		 icp->server_num,
		 old.cppr, old.mfrr, old.pending_pri, old.xisr,
		 old.need_resend, old.out_ee);
	XICS_DBG("UPD        - C:%02x M:%02x PP: %02x PI:%06x R:%d O:%d\n",
		 new.cppr, new.mfrr, new.pending_pri, new.xisr,
		 new.need_resend, new.out_ee);
	/*
	 * Check for output state update
	 *
	 * Note that this is racy since another processor could be updating
	 * the state already. This is why we never clear the interrupt output
	 * here, we only ever set it. The clear only happens prior to doing
	 * an update and only by the processor itself. Currently we do it
	 * in Accept (H_XIRR) and Up_Cppr (H_XPPR).
	 *
	 * We also do not try to figure out whether the EE state has changed,
	 * we unconditionally set it if the new state calls for it. The reason
	 * for that is that we opportunistically remove the pending interrupt
	 * flag when raising CPPR, so we need to set it back here if an
	 * interrupt is still pending.
	 */
	if (new.out_ee) {
		kvmppc_book3s_queue_irqprio(icp->vcpu,
					    BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
		if (!change_self)
			kvmppc_fast_vcpu_kick(icp->vcpu);
	}
 bail:
	return success;
}

static void icp_check_resend(struct kvmppc_xics *xics,
			     struct kvmppc_icp *icp)
{
	u32 icsid;

	/* Order this load with the test for need_resend in the caller */
	smp_rmb();
	for_each_set_bit(icsid, icp->resend_map, xics->max_icsid + 1) {
		struct kvmppc_ics *ics = xics->ics[icsid];

		if (!test_and_clear_bit(icsid, icp->resend_map))
			continue;
		if (!ics)
			continue;
		ics_check_resend(xics, ics, icp);
	}
}

static bool icp_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority,
			       u32 *reject)
{
	union kvmppc_icp_state old_state, new_state;
	bool success;

	XICS_DBG("try deliver %#x(P:%#x) to server %#x\n", irq, priority,
		 icp->server_num);

	do {
		old_state = new_state = ACCESS_ONCE(icp->state);

		*reject = 0;

		/* See if we can deliver */
		success = new_state.cppr > priority &&
			new_state.mfrr > priority &&
			new_state.pending_pri > priority;

		/*
		 * If we can, check for a rejection and perform the
		 * delivery
		 */
		if (success) {
			*reject = new_state.xisr;
			new_state.xisr = irq;
			new_state.pending_pri = priority;
		} else {
			/*
			 * If we failed to deliver we set need_resend
			 * so a subsequent CPPR state change causes us
			 * to try a new delivery.
			 */
			new_state.need_resend = true;
		}

	} while (!icp_try_update(icp, old_state, new_state, false));

	return success;
}

static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
			    u32 new_irq)
{
	struct ics_irq_state *state;
	struct kvmppc_ics *ics;
	u32 reject;
	u16 src;

	/*
	 * This is used both for initial delivery of an interrupt and
	 * for subsequent rejection.
	 *
	 * Rejection can be racy vs. resends. We have evaluated the
	 * rejection in an atomic ICP transaction which is now complete,
	 * so potentially the ICP can already accept the interrupt again.
	 *
	 * So we need to retry the delivery. Essentially the reject path
	 * boils down to a failed delivery. Always.
	 *
	 * Now the interrupt could also have moved to a different target,
	 * thus we may need to re-do the ICP lookup as well
	 */

 again:
	/* Get the ICS state and lock it */
	ics = kvmppc_xics_find_ics(xics, new_irq, &src);
	if (!ics) {
		XICS_DBG("icp_deliver_irq: IRQ 0x%06x not found !\n", new_irq);
		return;
	}
	state = &ics->irq_state[src];

	/* Get a lock on the ICS */
	mutex_lock(&ics->lock);

	/* Get our server */
	if (!icp || state->server != icp->server_num) {
		icp = kvmppc_xics_find_server(xics->kvm, state->server);
		if (!icp) {
			pr_warn("icp_deliver_irq: IRQ 0x%06x server 0x%x not found !\n",
				new_irq, state->server);
			goto out;
		}
	}

	/* Clear the resend bit of that interrupt */
	state->resend = 0;

	/*
	 * If masked, bail out
	 *
	 * Note: PAPR doesn't mention anything about masked pending
	 * when doing a resend, only when doing a delivery.
	 *
	 * However that would have the effect of losing a masked
	 * interrupt that was rejected and isn't consistent with
	 * the whole masked_pending business which is about not
	 * losing interrupts that occur while masked.
	 *
	 * I don't differenciate normal deliveries and resends, this
	 * implementation will differ from PAPR and not lose such
	 * interrupts.
	 */
	if (state->priority == MASKED) {
		XICS_DBG("irq %#x masked pending\n", new_irq);
		state->masked_pending = 1;
		goto out;
	}

	/*
	 * Try the delivery, this will set the need_resend flag
	 * in the ICP as part of the atomic transaction if the
	 * delivery is not possible.
	 *
	 * Note that if successful, the new delivery might have itself
	 * rejected an interrupt that was "delivered" before we took the
	 * icp mutex.
	 *
	 * In this case we do the whole sequence all over again for the
	 * new guy. We cannot assume that the rejected interrupt is less
	 * favored than the new one, and thus doesn't need to be delivered,
	 * because by the time we exit icp_try_to_deliver() the target
	 * processor may well have alrady consumed & completed it, and thus
	 * the rejected interrupt might actually be already acceptable.
	 */
	if (icp_try_to_deliver(icp, new_irq, state->priority, &reject)) {
		/*
		 * Delivery was successful, did we reject somebody else ?
		 */
		if (reject && reject != XICS_IPI) {
			mutex_unlock(&ics->lock);
			new_irq = reject;
			goto again;
		}
	} else {
		/*
		 * We failed to deliver the interrupt we need to set the
		 * resend map bit and mark the ICS state as needing a resend
		 */
		set_bit(ics->icsid, icp->resend_map);
		state->resend = 1;

		/*
		 * If the need_resend flag got cleared in the ICP some time
		 * between icp_try_to_deliver() atomic update and now, then
		 * we know it might have missed the resend_map bit. So we
		 * retry
		 */
		smp_mb();
		if (!icp->state.need_resend) {
			mutex_unlock(&ics->lock);
			goto again;
		}
	}
 out:
	mutex_unlock(&ics->lock);
}

static void icp_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
			  u8 new_cppr)
{
	union kvmppc_icp_state old_state, new_state;
	bool resend;

	/*
	 * This handles several related states in one operation:
	 *
	 * ICP State: Down_CPPR
	 *
	 * Load CPPR with new value and if the XISR is 0
	 * then check for resends:
	 *
	 * ICP State: Resend
	 *
	 * If MFRR is more favored than CPPR, check for IPIs
	 * and notify ICS of a potential resend. This is done
	 * asynchronously (when used in real mode, we will have
	 * to exit here).
	 *
	 * We do not handle the complete Check_IPI as documented
	 * here. In the PAPR, this state will be used for both
	 * Set_MFRR and Down_CPPR. However, we know that we aren't
	 * changing the MFRR state here so we don't need to handle
	 * the case of an MFRR causing a reject of a pending irq,
	 * this will have been handled when the MFRR was set in the
	 * first place.
	 *
	 * Thus we don't have to handle rejects, only resends.
	 *
	 * When implementing real mode for HV KVM, resend will lead to
	 * a H_TOO_HARD return and the whole transaction will be handled
	 * in virtual mode.
	 */
	do {
		old_state = new_state = ACCESS_ONCE(icp->state);

		/* Down_CPPR */
		new_state.cppr = new_cppr;

		/*
		 * Cut down Resend / Check_IPI / IPI
		 *
		 * The logic is that we cannot have a pending interrupt
		 * trumped by an IPI at this point (see above), so we
		 * know that either the pending interrupt is already an
		 * IPI (in which case we don't care to override it) or
		 * it's either more favored than us or non existent
		 */
		if (new_state.mfrr < new_cppr &&
		    new_state.mfrr <= new_state.pending_pri) {
			WARN_ON(new_state.xisr != XICS_IPI &&
				new_state.xisr != 0);
			new_state.pending_pri = new_state.mfrr;
			new_state.xisr = XICS_IPI;
		}

		/* Latch/clear resend bit */
		resend = new_state.need_resend;
		new_state.need_resend = 0;

	} while (!icp_try_update(icp, old_state, new_state, true));

	/*
	 * Now handle resend checks. Those are asynchronous to the ICP
	 * state update in HW (ie bus transactions) so we can handle them
	 * separately here too
	 */
	if (resend)
		icp_check_resend(xics, icp);
}

static noinline unsigned long kvmppc_h_xirr(struct kvm_vcpu *vcpu)
{
	union kvmppc_icp_state old_state, new_state;
	struct kvmppc_icp *icp = vcpu->arch.icp;
	u32 xirr;

	/* First, remove EE from the processor */
	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);

	/*
	 * ICP State: Accept_Interrupt
	 *
	 * Return the pending interrupt (if any) along with the
	 * current CPPR, then clear the XISR & set CPPR to the
	 * pending priority
	 */
	do {
		old_state = new_state = ACCESS_ONCE(icp->state);

		xirr = old_state.xisr | (((u32)old_state.cppr) << 24);
		if (!old_state.xisr)
			break;
		new_state.cppr = new_state.pending_pri;
		new_state.pending_pri = 0xff;
		new_state.xisr = 0;

	} while (!icp_try_update(icp, old_state, new_state, true));

	XICS_DBG("h_xirr vcpu %d xirr %#x\n", vcpu->vcpu_id, xirr);

	return xirr;
}

static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
				 unsigned long mfrr)
{
	union kvmppc_icp_state old_state, new_state;
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp;
	u32 reject;
	bool resend;
	bool local;

	XICS_DBG("h_ipi vcpu %d to server %lu mfrr %#lx\n",
		 vcpu->vcpu_id, server, mfrr);

	icp = vcpu->arch.icp;
	local = icp->server_num == server;
	if (!local) {
		icp = kvmppc_xics_find_server(vcpu->kvm, server);
		if (!icp)
			return H_PARAMETER;
	}

	/*
	 * ICP state: Set_MFRR
	 *
	 * If the CPPR is more favored than the new MFRR, then
	 * nothing needs to be rejected as there can be no XISR to
	 * reject.  If the MFRR is being made less favored then
	 * there might be a previously-rejected interrupt needing
	 * to be resent.
	 *
	 * If the CPPR is less favored, then we might be replacing
	 * an interrupt, and thus need to possibly reject it as in
	 *
	 * ICP state: Check_IPI
	 */
	do {
		old_state = new_state = ACCESS_ONCE(icp->state);

		/* Set_MFRR */
		new_state.mfrr = mfrr;

		/* Check_IPI */
		reject = 0;
		resend = false;
		if (mfrr < new_state.cppr) {
			/* Reject a pending interrupt if not an IPI */
			if (mfrr <= new_state.pending_pri)
				reject = new_state.xisr;
			new_state.pending_pri = mfrr;
			new_state.xisr = XICS_IPI;
		}

		if (mfrr > old_state.mfrr && mfrr > new_state.cppr) {
			resend = new_state.need_resend;
			new_state.need_resend = 0;
		}
	} while (!icp_try_update(icp, old_state, new_state, local));

	/* Handle reject */
	if (reject && reject != XICS_IPI)
		icp_deliver_irq(xics, icp, reject);

	/* Handle resend */
	if (resend)
		icp_check_resend(xics, icp);

	return H_SUCCESS;
}

static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
{
	union kvmppc_icp_state old_state, new_state;
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp = vcpu->arch.icp;
	u32 reject;

	XICS_DBG("h_cppr vcpu %d cppr %#lx\n", vcpu->vcpu_id, cppr);

	/*
	 * ICP State: Set_CPPR
	 *
	 * We can safely compare the new value with the current
	 * value outside of the transaction as the CPPR is only
	 * ever changed by the processor on itself
	 */
	if (cppr > icp->state.cppr)
		icp_down_cppr(xics, icp, cppr);
	else if (cppr == icp->state.cppr)
		return;

	/*
	 * ICP State: Up_CPPR
	 *
	 * The processor is raising its priority, this can result
	 * in a rejection of a pending interrupt:
	 *
	 * ICP State: Reject_Current
	 *
	 * We can remove EE from the current processor, the update
	 * transaction will set it again if needed
	 */
	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);

	do {
		old_state = new_state = ACCESS_ONCE(icp->state);

		reject = 0;
		new_state.cppr = cppr;

		if (cppr <= new_state.pending_pri) {
			reject = new_state.xisr;
			new_state.xisr = 0;
			new_state.pending_pri = 0xff;
		}

	} while (!icp_try_update(icp, old_state, new_state, true));

	/*
	 * Check for rejects. They are handled by doing a new delivery
	 * attempt (see comments in icp_deliver_irq).
	 */
	if (reject && reject != XICS_IPI)
		icp_deliver_irq(xics, icp, reject);
}

static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
{
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp = vcpu->arch.icp;
	struct kvmppc_ics *ics;
	struct ics_irq_state *state;
	u32 irq = xirr & 0x00ffffff;
	u16 src;

	XICS_DBG("h_eoi vcpu %d eoi %#lx\n", vcpu->vcpu_id, xirr);

	/*
	 * ICP State: EOI
	 *
	 * Note: If EOI is incorrectly used by SW to lower the CPPR
	 * value (ie more favored), we do not check for rejection of
	 * a pending interrupt, this is a SW error and PAPR sepcifies
	 * that we don't have to deal with it.
	 *
	 * The sending of an EOI to the ICS is handled after the
	 * CPPR update
	 *
	 * ICP State: Down_CPPR which we handle
	 * in a separate function as it's shared with H_CPPR.
	 */
	icp_down_cppr(xics, icp, xirr >> 24);

	/* IPIs have no EOI */
	if (irq == XICS_IPI)
		return H_SUCCESS;
	/*
	 * EOI handling: If the interrupt is still asserted, we need to
	 * resend it. We can take a lockless "peek" at the ICS state here.
	 *
	 * "Message" interrupts will never have "asserted" set
	 */
	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics) {
		XICS_DBG("h_eoi: IRQ 0x%06x not found !\n", irq);
		return H_PARAMETER;
	}
	state = &ics->irq_state[src];

	/* Still asserted, resend it */
	if (state->asserted)
		icp_deliver_irq(xics, icp, irq);

	return H_SUCCESS;
}

static noinline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall)
{
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp = vcpu->arch.icp;

	XICS_DBG("XICS_RM: H_%x completing, act: %x state: %lx tgt: %p\n",
		 hcall, icp->rm_action, icp->rm_dbgstate.raw, icp->rm_dbgtgt);

	if (icp->rm_action & XICS_RM_KICK_VCPU)
		kvmppc_fast_vcpu_kick(icp->rm_kick_target);
	if (icp->rm_action & XICS_RM_CHECK_RESEND)
		icp_check_resend(xics, icp);
	if (icp->rm_action & XICS_RM_REJECT)
		icp_deliver_irq(xics, icp, icp->rm_reject);

	icp->rm_action = 0;

	return H_SUCCESS;
}

int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
{
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	unsigned long res;
	int rc = H_SUCCESS;

	/* Check if we have an ICP */
	if (!xics || !vcpu->arch.icp)
		return H_HARDWARE;

	/* Check for real mode returning too hard */
	if (xics->real_mode)
		return kvmppc_xics_rm_complete(vcpu, req);

	switch (req) {
	case H_XIRR:
		res = kvmppc_h_xirr(vcpu);
		kvmppc_set_gpr(vcpu, 4, res);
		break;
	case H_CPPR:
		kvmppc_h_cppr(vcpu, kvmppc_get_gpr(vcpu, 4));
		break;
	case H_EOI:
		rc = kvmppc_h_eoi(vcpu, kvmppc_get_gpr(vcpu, 4));
		break;
	case H_IPI:
		rc = kvmppc_h_ipi(vcpu, kvmppc_get_gpr(vcpu, 4),
				  kvmppc_get_gpr(vcpu, 5));
		break;
	}

	return rc;
}


/* -- Initialisation code etc. -- */

static int xics_debug_show(struct seq_file *m, void *private)
{
	struct kvmppc_xics *xics = m->private;
	struct kvm *kvm = xics->kvm;
	struct kvm_vcpu *vcpu;
	int icsid, i;

	if (!kvm)
		return 0;

	seq_printf(m, "=========\nICP state\n=========\n");

	kvm_for_each_vcpu(i, vcpu, kvm) {
		struct kvmppc_icp *icp = vcpu->arch.icp;
		union kvmppc_icp_state state;

		if (!icp)
			continue;

		state.raw = ACCESS_ONCE(icp->state.raw);
		seq_printf(m, "cpu server %#lx XIRR:%#x PPRI:%#x CPPR:%#x MFRR:%#x OUT:%d NR:%d\n",
			   icp->server_num, state.xisr,
			   state.pending_pri, state.cppr, state.mfrr,
			   state.out_ee, state.need_resend);
	}

	for (icsid = 0; icsid <= KVMPPC_XICS_MAX_ICS_ID; icsid++) {
		struct kvmppc_ics *ics = xics->ics[icsid];

		if (!ics)
			continue;

		seq_printf(m, "=========\nICS state for ICS 0x%x\n=========\n",
			   icsid);

		mutex_lock(&ics->lock);

		for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
			struct ics_irq_state *irq = &ics->irq_state[i];

			seq_printf(m, "irq 0x%06x: server %#x prio %#x save prio %#x asserted %d resend %d masked pending %d\n",
				   irq->number, irq->server, irq->priority,
				   irq->saved_priority, irq->asserted,
				   irq->resend, irq->masked_pending);

		}
		mutex_unlock(&ics->lock);
	}
	return 0;
}

static int xics_debug_open(struct inode *inode, struct file *file)
{
	return single_open(file, xics_debug_show, inode->i_private);
}

static const struct file_operations xics_debug_fops = {
	.open = xics_debug_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

static void xics_debugfs_init(struct kvmppc_xics *xics)
{
	char *name;

	name = kasprintf(GFP_KERNEL, "kvm-xics-%p", xics);
	if (!name) {
		pr_err("%s: no memory for name\n", __func__);
		return;
	}

	xics->dentry = debugfs_create_file(name, S_IRUGO, powerpc_debugfs_root,
					   xics, &xics_debug_fops);

	pr_debug("%s: created %s\n", __func__, name);
	kfree(name);
}

struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm,
					  struct kvmppc_xics *xics, int irq)
{
	struct kvmppc_ics *ics;
	int i, icsid;

	icsid = irq >> KVMPPC_XICS_ICS_SHIFT;

	mutex_lock(&kvm->lock);

	/* ICS already exists - somebody else got here first */
	if (xics->ics[icsid])
		goto out;

	/* Create the ICS */
	ics = kzalloc(sizeof(struct kvmppc_ics), GFP_KERNEL);
	if (!ics)
		goto out;

	mutex_init(&ics->lock);
	ics->icsid = icsid;

	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
		ics->irq_state[i].number = (icsid << KVMPPC_XICS_ICS_SHIFT) | i;
		ics->irq_state[i].priority = MASKED;
		ics->irq_state[i].saved_priority = MASKED;
	}
	smp_wmb();
	xics->ics[icsid] = ics;

	if (icsid > xics->max_icsid)
		xics->max_icsid = icsid;

 out:
	mutex_unlock(&kvm->lock);
	return xics->ics[icsid];
}

int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server_num)
{
	struct kvmppc_icp *icp;

	if (!vcpu->kvm->arch.xics)
		return -ENODEV;

	if (kvmppc_xics_find_server(vcpu->kvm, server_num))
		return -EEXIST;

	icp = kzalloc(sizeof(struct kvmppc_icp), GFP_KERNEL);
	if (!icp)
		return -ENOMEM;

	icp->vcpu = vcpu;
	icp->server_num = server_num;
	icp->state.mfrr = MASKED;
	icp->state.pending_pri = MASKED;
	vcpu->arch.icp = icp;

	XICS_DBG("created server for vcpu %d\n", vcpu->vcpu_id);

	return 0;
}

/* -- ioctls -- */

int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args)
{
	struct kvmppc_xics *xics;
	int r;

	/* locking against multiple callers? */

	xics = kvm->arch.xics;
	if (!xics)
		return -ENODEV;

	switch (args->level) {
	case KVM_INTERRUPT_SET:
	case KVM_INTERRUPT_SET_LEVEL:
	case KVM_INTERRUPT_UNSET:
		r = ics_deliver_irq(xics, args->irq, args->level);
		break;
	default:
		r = -EINVAL;
	}

	return r;
}

void kvmppc_xics_free(struct kvmppc_xics *xics)
{
	int i;
	struct kvm *kvm = xics->kvm;

	debugfs_remove(xics->dentry);

	if (kvm)
		kvm->arch.xics = NULL;

	for (i = 0; i <= xics->max_icsid; i++)
		kfree(xics->ics[i]);
	kfree(xics);
}

int kvm_xics_create(struct kvm *kvm, u32 type)
{
	struct kvmppc_xics *xics;
	int ret = 0;

	xics = kzalloc(sizeof(*xics), GFP_KERNEL);
	if (!xics)
		return -ENOMEM;

	xics->kvm = kvm;

	/* Already there ? */
	mutex_lock(&kvm->lock);
	if (kvm->arch.xics)
		ret = -EEXIST;
	else
		kvm->arch.xics = xics;
	mutex_unlock(&kvm->lock);

	if (ret)
		return ret;

	xics_debugfs_init(xics);

#ifdef CONFIG_KVM_BOOK3S_64_HV
	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
		/* Enable real mode support */
		xics->real_mode = ENABLE_REALMODE;
		xics->real_mode_dbg = DEBUG_REALMODE;
	}
#endif /* CONFIG_KVM_BOOK3S_64_HV */

	return 0;
}

void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu)
{
	if (!vcpu->arch.icp)
		return;
	kfree(vcpu->arch.icp);
	vcpu->arch.icp = NULL;
	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
}