aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_hv_rm_xics.c
blob: a8e3498a853f600ca1c6a46ae15e74e9bd30c09a (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
/*
 * 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/kernel_stat.h>

#include <asm/kvm_book3s.h>
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/xics.h>
#include <asm/debug.h>
#include <asm/synch.h>
#include <asm/cputhreads.h>
#include <asm/pgtable.h>
#include <asm/ppc-opcode.h>
#include <asm/pnv-pci.h>
#include <asm/opal.h>
#include <asm/smp.h>

#include "book3s_xics.h"

#define DEBUG_PASSUP

int h_ipi_redirect = 1;
EXPORT_SYMBOL(h_ipi_redirect);
int kvm_irq_bypass = 1;
EXPORT_SYMBOL(kvm_irq_bypass);

static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
			    u32 new_irq);
static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu);

/* -- ICS routines -- */
static void ics_rm_check_resend(struct kvmppc_xics *xics,
				struct kvmppc_ics *ics, struct kvmppc_icp *icp)
{
	int i;

	arch_spin_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;

		arch_spin_unlock(&ics->lock);
		icp_rm_deliver_irq(xics, icp, state->number);
		arch_spin_lock(&ics->lock);
	}

	arch_spin_unlock(&ics->lock);
}

/* -- ICP routines -- */

#ifdef CONFIG_SMP
static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu)
{
	int hcpu;

	hcpu = hcore << threads_shift;
	kvmppc_host_rm_ops_hv->rm_core[hcore].rm_data = vcpu;
	smp_muxed_ipi_set_message(hcpu, PPC_MSG_RM_HOST_ACTION);
	icp_native_cause_ipi_rm(hcpu);
}
#else
static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu) { }
#endif

/*
 * We start the search from our current CPU Id in the core map
 * and go in a circle until we get back to our ID looking for a
 * core that is running in host context and that hasn't already
 * been targeted for another rm_host_ops.
 *
 * In the future, could consider using a fairer algorithm (one
 * that distributes the IPIs better)
 *
 * Returns -1, if no CPU could be found in the host
 * Else, returns a CPU Id which has been reserved for use
 */
static inline int grab_next_hostcore(int start,
		struct kvmppc_host_rm_core *rm_core, int max, int action)
{
	bool success;
	int core;
	union kvmppc_rm_state old, new;

	for (core = start + 1; core < max; core++)  {
		old = new = READ_ONCE(rm_core[core].rm_state);

		if (!old.in_host || old.rm_action)
			continue;

		/* Try to grab this host core if not taken already. */
		new.rm_action = action;

		success = cmpxchg64(&rm_core[core].rm_state.raw,
						old.raw, new.raw) == old.raw;
		if (success) {
			/*
			 * Make sure that the store to the rm_action is made
			 * visible before we return to caller (and the
			 * subsequent store to rm_data) to synchronize with
			 * the IPI handler.
			 */
			smp_wmb();
			return core;
		}
	}

	return -1;
}

static inline int find_available_hostcore(int action)
{
	int core;
	int my_core = smp_processor_id() >> threads_shift;
	struct kvmppc_host_rm_core *rm_core = kvmppc_host_rm_ops_hv->rm_core;

	core = grab_next_hostcore(my_core, rm_core, cpu_nr_cores(), action);
	if (core == -1)
		core = grab_next_hostcore(core, rm_core, my_core, action);

	return core;
}

static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
				struct kvm_vcpu *this_vcpu)
{
	struct kvmppc_icp *this_icp = this_vcpu->arch.icp;
	int cpu;
	int hcore;

	/* Mark the target VCPU as having an interrupt pending */
	vcpu->stat.queue_intr++;
	set_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);

	/* Kick self ? Just set MER and return */
	if (vcpu == this_vcpu) {
		mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_MER);
		return;
	}

	/*
	 * Check if the core is loaded,
	 * if not, find an available host core to post to wake the VCPU,
	 * if we can't find one, set up state to eventually return too hard.
	 */
	cpu = vcpu->arch.thread_cpu;
	if (cpu < 0 || cpu >= nr_cpu_ids) {
		hcore = -1;
		if (kvmppc_host_rm_ops_hv && h_ipi_redirect)
			hcore = find_available_hostcore(XICS_RM_KICK_VCPU);
		if (hcore != -1) {
			icp_send_hcore_msg(hcore, vcpu);
		} else {
			this_icp->rm_action |= XICS_RM_KICK_VCPU;
			this_icp->rm_kick_target = vcpu;
		}
		return;
	}

	smp_mb();
	kvmhv_rm_send_ipi(cpu);
}

static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu)
{
	/* Note: Only called on self ! */
	clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
		  &vcpu->arch.pending_exceptions);
	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_MER);
}

static inline bool icp_rm_try_update(struct kvmppc_icp *icp,
				     union kvmppc_icp_state old,
				     union kvmppc_icp_state new)
{
	struct kvm_vcpu *this_vcpu = local_paca->kvm_hstate.kvm_vcpu;
	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;

	/*
	 * 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)
		icp_rm_set_vcpu_irq(icp->vcpu, this_vcpu);

	/* Expose the state change for debug purposes */
	this_vcpu->arch.icp->rm_dbgstate = new;
	this_vcpu->arch.icp->rm_dbgtgt = icp->vcpu;

 bail:
	return success;
}

static inline int check_too_hard(struct kvmppc_xics *xics,
				 struct kvmppc_icp *icp)
{
	return (xics->real_mode_dbg || icp->rm_action) ? H_TOO_HARD : H_SUCCESS;
}

static void icp_rm_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_rm_check_resend(xics, ics, icp);
	}
}

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

	do {
		old_state = new_state = READ_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_rm_try_update(icp, old_state, new_state));

	return success;
}

static void icp_rm_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) {
		/* Unsafe increment, but this does not need to be accurate */
		xics->err_noics++;
		return;
	}
	state = &ics->irq_state[src];

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

	/* Get our server */
	if (!icp || state->server != icp->server_num) {
		icp = kvmppc_xics_find_server(xics->kvm, state->server);
		if (!icp) {
			/* Unsafe increment again*/
			xics->err_noicp++;
			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 differentiate normal deliveries and resends, this
	 * implementation will differ from PAPR and not lose such
	 * interrupts.
	 */
	if (state->priority == MASKED) {
		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
	 * ics spin lock.
	 *
	 * 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_rm_try_to_deliver() the target
	 * processor may well have already consumed & completed it, and thus
	 * the rejected interrupt might actually be already acceptable.
	 */
	if (icp_rm_try_to_deliver(icp, new_irq, state->priority, &reject)) {
		/*
		 * Delivery was successful, did we reject somebody else ?
		 */
		if (reject && reject != XICS_IPI) {
			arch_spin_unlock(&ics->lock);
			icp->n_reject++;
			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_rm_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) {
			arch_spin_unlock(&ics->lock);
			goto again;
		}
	}
 out:
	arch_spin_unlock(&ics->lock);
}

static void icp_rm_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 = READ_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) {
			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_rm_try_update(icp, old_state, new_state));

	/*
	 * Now handle resend checks. Those are asynchronous to the ICP
	 * state update in HW (ie bus transactions) so we can handle them
	 * separately here as well.
	 */
	if (resend) {
		icp->n_check_resend++;
		icp_rm_check_resend(xics, icp);
	}
}


unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
{
	union kvmppc_icp_state old_state, new_state;
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp = vcpu->arch.icp;
	u32 xirr;

	if (!xics || !xics->real_mode)
		return H_TOO_HARD;

	/* First clear the interrupt */
	icp_rm_clr_vcpu_irq(icp->vcpu);

	/*
	 * 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 = READ_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_rm_try_update(icp, old_state, new_state));

	/* Return the result in GPR4 */
	vcpu->arch.gpr[4] = xirr;

	return check_too_hard(xics, icp);
}

int kvmppc_rm_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, *this_icp = vcpu->arch.icp;
	u32 reject;
	bool resend;
	bool local;

	if (!xics || !xics->real_mode)
		return H_TOO_HARD;

	local = this_icp->server_num == server;
	if (local)
		icp = this_icp;
	else
		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 done as there can be no XISR to
	 * reject.
	 *
	 * ICP state: Check_IPI
	 *
	 * If the CPPR is less favored, then we might be replacing
	 * an interrupt, and thus need to possibly reject it.
	 *
	 * ICP State: IPI
	 *
	 * Besides rejecting any pending interrupts, we also
	 * update XISR and pending_pri to mark IPI as pending.
	 *
	 * PAPR does not describe this state, but if the MFRR is being
	 * made less favored than its earlier value, there might be
	 * a previously-rejected interrupt needing to be resent.
	 * Ideally, we would want to resend only if
	 *	prio(pending_interrupt) < mfrr &&
	 *	prio(pending_interrupt) < cppr
	 * where pending interrupt is the one that was rejected. But
	 * we don't have that state, so we simply trigger a resend
	 * whenever the MFRR is made less favored.
	 */
	do {
		old_state = new_state = READ_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) {
			resend = new_state.need_resend;
			new_state.need_resend = 0;
		}
	} while (!icp_rm_try_update(icp, old_state, new_state));

	/* Handle reject in real mode */
	if (reject && reject != XICS_IPI) {
		this_icp->n_reject++;
		icp_rm_deliver_irq(xics, icp, reject);
	}

	/* Handle resends in real mode */
	if (resend) {
		this_icp->n_check_resend++;
		icp_rm_check_resend(xics, icp);
	}

	return check_too_hard(xics, this_icp);
}

int kvmppc_rm_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;

	if (!xics || !xics->real_mode)
		return H_TOO_HARD;

	/*
	 * 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_rm_down_cppr(xics, icp, cppr);
		goto bail;
	} else if (cppr == icp->state.cppr)
		return H_SUCCESS;

	/*
	 * 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
	 */
	icp_rm_clr_vcpu_irq(icp->vcpu);

	do {
		old_state = new_state = READ_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_rm_try_update(icp, old_state, new_state));

	/*
	 * Check for rejects. They are handled by doing a new delivery
	 * attempt (see comments in icp_rm_deliver_irq).
	 */
	if (reject && reject != XICS_IPI) {
		icp->n_reject++;
		icp_rm_deliver_irq(xics, icp, reject);
	}
 bail:
	return check_too_hard(xics, icp);
}

int kvmppc_rm_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;

	if (!xics || !xics->real_mode)
		return H_TOO_HARD;

	/*
	 * 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_rm_down_cppr(xics, icp, xirr >> 24);

	/* IPIs have no EOI */
	if (irq == XICS_IPI)
		goto bail;
	/*
	 * 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)
		goto bail;
	state = &ics->irq_state[src];

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

	if (!hlist_empty(&vcpu->kvm->irq_ack_notifier_list)) {
		icp->rm_action |= XICS_RM_NOTIFY_EOI;
		icp->rm_eoied_irq = irq;
	}

	if (state->host_irq) {
		++vcpu->stat.pthru_all;
		if (state->intr_cpu != -1) {
			int pcpu = raw_smp_processor_id();

			pcpu = cpu_first_thread_sibling(pcpu);
			++vcpu->stat.pthru_host;
			if (state->intr_cpu != pcpu) {
				++vcpu->stat.pthru_bad_aff;
				xics_opal_rm_set_server(state->host_irq, pcpu);
			}
			state->intr_cpu = -1;
		}
	}
 bail:
	return check_too_hard(xics, icp);
}

unsigned long eoi_rc;

static void icp_eoi(struct irq_chip *c, u32 hwirq, u32 xirr)
{
	unsigned long xics_phys;
	int64_t rc;

	rc = pnv_opal_pci_msi_eoi(c, hwirq);

	if (rc)
		eoi_rc = rc;

	iosync();

	/* EOI it */
	xics_phys = local_paca->kvm_hstate.xics_phys;
	_stwcix(xics_phys + XICS_XIRR, xirr);
}

static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu)
{
	unsigned int mangle_cpu = get_hard_smp_processor_id(server_cpu) << 2;

	return opal_rm_set_xive(hw_irq, mangle_cpu, DEFAULT_PRIORITY);
}

/*
 * Increment a per-CPU 32-bit unsigned integer variable.
 * Safe to call in real-mode. Handles vmalloc'ed addresses
 *
 * ToDo: Make this work for any integral type
 */

static inline void this_cpu_inc_rm(unsigned int __percpu *addr)
{
	unsigned long l;
	unsigned int *raddr;
	int cpu = smp_processor_id();

	raddr = per_cpu_ptr(addr, cpu);
	l = (unsigned long)raddr;

	if (REGION_ID(l) == VMALLOC_REGION_ID) {
		l = vmalloc_to_phys(raddr);
		raddr = (unsigned int *)l;
	}
	++*raddr;
}

/*
 * We don't try to update the flags in the irq_desc 'istate' field in
 * here as would happen in the normal IRQ handling path for several reasons:
 *  - state flags represent internal IRQ state and are not expected to be
 *    updated outside the IRQ subsystem
 *  - more importantly, these are useful for edge triggered interrupts,
 *    IRQ probing, etc., but we are only handling MSI/MSIx interrupts here
 *    and these states shouldn't apply to us.
 *
 * However, we do update irq_stats - we somewhat duplicate the code in
 * kstat_incr_irqs_this_cpu() for this since this function is defined
 * in irq/internal.h which we don't want to include here.
 * The only difference is that desc->kstat_irqs is an allocated per CPU
 * variable and could have been vmalloc'ed, so we can't directly
 * call __this_cpu_inc() on it. The kstat structure is a static
 * per CPU variable and it should be accessible by real-mode KVM.
 *
 */
static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc)
{
	this_cpu_inc_rm(desc->kstat_irqs);
	__this_cpu_inc(kstat.irqs_sum);
}

long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
				 u32 xirr,
				 struct kvmppc_irq_map *irq_map,
				 struct kvmppc_passthru_irqmap *pimap)
{
	struct kvmppc_xics *xics;
	struct kvmppc_icp *icp;
	u32 irq;

	irq = irq_map->v_hwirq;
	xics = vcpu->kvm->arch.xics;
	icp = vcpu->arch.icp;

	kvmppc_rm_handle_irq_desc(irq_map->desc);
	icp_rm_deliver_irq(xics, icp, irq);

	/* EOI the interrupt */
	icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr);

	if (check_too_hard(xics, icp) == H_TOO_HARD)
		return 2;
	else
		return -2;
}

/*  --- Non-real mode XICS-related built-in routines ---  */

/**
 * Host Operations poked by RM KVM
 */
static void rm_host_ipi_action(int action, void *data)
{
	switch (action) {
	case XICS_RM_KICK_VCPU:
		kvmppc_host_rm_ops_hv->vcpu_kick(data);
		break;
	default:
		WARN(1, "Unexpected rm_action=%d data=%p\n", action, data);
		break;
	}

}

void kvmppc_xics_ipi_action(void)
{
	int core;
	unsigned int cpu = smp_processor_id();
	struct kvmppc_host_rm_core *rm_corep;

	core = cpu >> threads_shift;
	rm_corep = &kvmppc_host_rm_ops_hv->rm_core[core];

	if (rm_corep->rm_data) {
		rm_host_ipi_action(rm_corep->rm_state.rm_action,
							rm_corep->rm_data);
		/* Order these stores against the real mode KVM */
		rm_corep->rm_data = NULL;
		smp_wmb();
		rm_corep->rm_state.rm_action = 0;
	}
}