1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright 2012 Michael Ellerman, IBM Corporation.
4 * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation.
5 */
6
7#include <linux/kernel.h>
8#include <linux/kvm_host.h>
9#include <linux/err.h>
10#include <linux/gfp.h>
11#include <linux/anon_inodes.h>
12#include <linux/spinlock.h>
13
14#include <linux/uaccess.h>
15#include <asm/kvm_book3s.h>
16#include <asm/kvm_ppc.h>
17#include <asm/hvcall.h>
18#include <asm/xics.h>
19#include <asm/debugfs.h>
20#include <asm/time.h>
21
22#include <linux/seq_file.h>
23
24#include "book3s_xics.h"
25
26#if 1
27#define XICS_DBG(fmt...) do { } while (0)
28#else
29#define XICS_DBG(fmt...) trace_printk(fmt)
30#endif
31
32#define ENABLE_REALMODE	true
33#define DEBUG_REALMODE	false
34
35/*
36 * LOCKING
37 * =======
38 *
39 * Each ICS has a spin lock protecting the information about the IRQ
40 * sources and avoiding simultaneous deliveries of the same interrupt.
41 *
42 * ICP operations are done via a single compare & swap transaction
43 * (most ICP state fits in the union kvmppc_icp_state)
44 */
45
46/*
47 * TODO
48 * ====
49 *
50 * - To speed up resends, keep a bitmap of "resend" set bits in the
51 *   ICS
52 *
53 * - Speed up server# -> ICP lookup (array ? hash table ?)
54 *
55 * - Make ICS lockless as well, or at least a per-interrupt lock or hashed
56 *   locks array to improve scalability
57 */
58
59/* -- ICS routines -- */
60
61static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
62			    u32 new_irq, bool check_resend);
63
64/*
65 * Return value ideally indicates how the interrupt was handled, but no
66 * callers look at it (given that we don't implement KVM_IRQ_LINE_STATUS),
67 * so just return 0.
68 */
69static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level)
70{
71	struct ics_irq_state *state;
72	struct kvmppc_ics *ics;
73	u16 src;
74	u32 pq_old, pq_new;
75
76	XICS_DBG("ics deliver %#x (level: %d)\n", irq, level);
77
78	ics = kvmppc_xics_find_ics(xics, irq, &src);
79	if (!ics) {
80		XICS_DBG("ics_deliver_irq: IRQ 0x%06x not found !\n", irq);
81		return -EINVAL;
82	}
83	state = &ics->irq_state[src];
84	if (!state->exists)
85		return -EINVAL;
86
87	if (level == KVM_INTERRUPT_SET_LEVEL || level == KVM_INTERRUPT_SET)
88		level = 1;
89	else if (level == KVM_INTERRUPT_UNSET)
90		level = 0;
91	/*
92	 * Take other values the same as 1, consistent with original code.
93	 * maybe WARN here?
94	 */
95
96	if (!state->lsi && level == 0) /* noop for MSI */
97		return 0;
98
99	do {
100		pq_old = state->pq_state;
101		if (state->lsi) {
102			if (level) {
103				if (pq_old & PQ_PRESENTED)
104					/* Setting already set LSI ... */
105					return 0;
106
107				pq_new = PQ_PRESENTED;
108			} else
109				pq_new = 0;
110		} else
111			pq_new = ((pq_old << 1) & 3) | PQ_PRESENTED;
112	} while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old);
113
114	/* Test P=1, Q=0, this is the only case where we present */
115	if (pq_new == PQ_PRESENTED)
116		icp_deliver_irq(xics, NULL, irq, false);
117
118	/* Record which CPU this arrived on for passed-through interrupts */
119	if (state->host_irq)
120		state->intr_cpu = raw_smp_processor_id();
121
122	return 0;
123}
124
125static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
126			     struct kvmppc_icp *icp)
127{
128	int i;
129
130	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
131		struct ics_irq_state *state = &ics->irq_state[i];
132		if (state->resend) {
133			XICS_DBG("resend %#x prio %#x\n", state->number,
134				      state->priority);
135			icp_deliver_irq(xics, icp, state->number, true);
136		}
137	}
138}
139
140static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
141		       struct ics_irq_state *state,
142		       u32 server, u32 priority, u32 saved_priority)
143{
144	bool deliver;
145	unsigned long flags;
146
147	local_irq_save(flags);
148	arch_spin_lock(&ics->lock);
149
150	state->server = server;
151	state->priority = priority;
152	state->saved_priority = saved_priority;
153	deliver = false;
154	if ((state->masked_pending || state->resend) && priority != MASKED) {
155		state->masked_pending = 0;
156		state->resend = 0;
157		deliver = true;
158	}
159
160	arch_spin_unlock(&ics->lock);
161	local_irq_restore(flags);
162
163	return deliver;
164}
165
166int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priority)
167{
168	struct kvmppc_xics *xics = kvm->arch.xics;
169	struct kvmppc_icp *icp;
170	struct kvmppc_ics *ics;
171	struct ics_irq_state *state;
172	u16 src;
173
174	if (!xics)
175		return -ENODEV;
176
177	ics = kvmppc_xics_find_ics(xics, irq, &src);
178	if (!ics)
179		return -EINVAL;
180	state = &ics->irq_state[src];
181
182	icp = kvmppc_xics_find_server(kvm, server);
183	if (!icp)
184		return -EINVAL;
185
186	XICS_DBG("set_xive %#x server %#x prio %#x MP:%d RS:%d\n",
187		 irq, server, priority,
188		 state->masked_pending, state->resend);
189
190	if (write_xive(xics, ics, state, server, priority, priority))
191		icp_deliver_irq(xics, icp, irq, false);
192
193	return 0;
194}
195
196int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority)
197{
198	struct kvmppc_xics *xics = kvm->arch.xics;
199	struct kvmppc_ics *ics;
200	struct ics_irq_state *state;
201	u16 src;
202	unsigned long flags;
203
204	if (!xics)
205		return -ENODEV;
206
207	ics = kvmppc_xics_find_ics(xics, irq, &src);
208	if (!ics)
209		return -EINVAL;
210	state = &ics->irq_state[src];
211
212	local_irq_save(flags);
213	arch_spin_lock(&ics->lock);
214	*server = state->server;
215	*priority = state->priority;
216	arch_spin_unlock(&ics->lock);
217	local_irq_restore(flags);
218
219	return 0;
220}
221
222int kvmppc_xics_int_on(struct kvm *kvm, u32 irq)
223{
224	struct kvmppc_xics *xics = kvm->arch.xics;
225	struct kvmppc_icp *icp;
226	struct kvmppc_ics *ics;
227	struct ics_irq_state *state;
228	u16 src;
229
230	if (!xics)
231		return -ENODEV;
232
233	ics = kvmppc_xics_find_ics(xics, irq, &src);
234	if (!ics)
235		return -EINVAL;
236	state = &ics->irq_state[src];
237
238	icp = kvmppc_xics_find_server(kvm, state->server);
239	if (!icp)
240		return -EINVAL;
241
242	if (write_xive(xics, ics, state, state->server, state->saved_priority,
243		       state->saved_priority))
244		icp_deliver_irq(xics, icp, irq, false);
245
246	return 0;
247}
248
249int kvmppc_xics_int_off(struct kvm *kvm, u32 irq)
250{
251	struct kvmppc_xics *xics = kvm->arch.xics;
252	struct kvmppc_ics *ics;
253	struct ics_irq_state *state;
254	u16 src;
255
256	if (!xics)
257		return -ENODEV;
258
259	ics = kvmppc_xics_find_ics(xics, irq, &src);
260	if (!ics)
261		return -EINVAL;
262	state = &ics->irq_state[src];
263
264	write_xive(xics, ics, state, state->server, MASKED, state->priority);
265
266	return 0;
267}
268
269/* -- ICP routines, including hcalls -- */
270
271static inline bool icp_try_update(struct kvmppc_icp *icp,
272				  union kvmppc_icp_state old,
273				  union kvmppc_icp_state new,
274				  bool change_self)
275{
276	bool success;
277
278	/* Calculate new output value */
279	new.out_ee = (new.xisr && (new.pending_pri < new.cppr));
280
281	/* Attempt atomic update */
282	success = cmpxchg64(&icp->state.raw, old.raw, new.raw) == old.raw;
283	if (!success)
284		goto bail;
285
286	XICS_DBG("UPD [%04lx] - C:%02x M:%02x PP: %02x PI:%06x R:%d O:%d\n",
287		 icp->server_num,
288		 old.cppr, old.mfrr, old.pending_pri, old.xisr,
289		 old.need_resend, old.out_ee);
290	XICS_DBG("UPD        - C:%02x M:%02x PP: %02x PI:%06x R:%d O:%d\n",
291		 new.cppr, new.mfrr, new.pending_pri, new.xisr,
292		 new.need_resend, new.out_ee);
293	/*
294	 * Check for output state update
295	 *
296	 * Note that this is racy since another processor could be updating
297	 * the state already. This is why we never clear the interrupt output
298	 * here, we only ever set it. The clear only happens prior to doing
299	 * an update and only by the processor itself. Currently we do it
300	 * in Accept (H_XIRR) and Up_Cppr (H_XPPR).
301	 *
302	 * We also do not try to figure out whether the EE state has changed,
303	 * we unconditionally set it if the new state calls for it. The reason
304	 * for that is that we opportunistically remove the pending interrupt
305	 * flag when raising CPPR, so we need to set it back here if an
306	 * interrupt is still pending.
307	 */
308	if (new.out_ee) {
309		kvmppc_book3s_queue_irqprio(icp->vcpu,
310					    BOOK3S_INTERRUPT_EXTERNAL);
311		if (!change_self)
312			kvmppc_fast_vcpu_kick(icp->vcpu);
313	}
314 bail:
315	return success;
316}
317
318static void icp_check_resend(struct kvmppc_xics *xics,
319			     struct kvmppc_icp *icp)
320{
321	u32 icsid;
322
323	/* Order this load with the test for need_resend in the caller */
324	smp_rmb();
325	for_each_set_bit(icsid, icp->resend_map, xics->max_icsid + 1) {
326		struct kvmppc_ics *ics = xics->ics[icsid];
327
328		if (!test_and_clear_bit(icsid, icp->resend_map))
329			continue;
330		if (!ics)
331			continue;
332		ics_check_resend(xics, ics, icp);
333	}
334}
335
336static bool icp_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority,
337			       u32 *reject)
338{
339	union kvmppc_icp_state old_state, new_state;
340	bool success;
341
342	XICS_DBG("try deliver %#x(P:%#x) to server %#lx\n", irq, priority,
343		 icp->server_num);
344
345	do {
346		old_state = new_state = READ_ONCE(icp->state);
347
348		*reject = 0;
349
350		/* See if we can deliver */
351		success = new_state.cppr > priority &&
352			new_state.mfrr > priority &&
353			new_state.pending_pri > priority;
354
355		/*
356		 * If we can, check for a rejection and perform the
357		 * delivery
358		 */
359		if (success) {
360			*reject = new_state.xisr;
361			new_state.xisr = irq;
362			new_state.pending_pri = priority;
363		} else {
364			/*
365			 * If we failed to deliver we set need_resend
366			 * so a subsequent CPPR state change causes us
367			 * to try a new delivery.
368			 */
369			new_state.need_resend = true;
370		}
371
372	} while (!icp_try_update(icp, old_state, new_state, false));
373
374	return success;
375}
376
377static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
378			    u32 new_irq, bool check_resend)
379{
380	struct ics_irq_state *state;
381	struct kvmppc_ics *ics;
382	u32 reject;
383	u16 src;
384	unsigned long flags;
385
386	/*
387	 * This is used both for initial delivery of an interrupt and
388	 * for subsequent rejection.
389	 *
390	 * Rejection can be racy vs. resends. We have evaluated the
391	 * rejection in an atomic ICP transaction which is now complete,
392	 * so potentially the ICP can already accept the interrupt again.
393	 *
394	 * So we need to retry the delivery. Essentially the reject path
395	 * boils down to a failed delivery. Always.
396	 *
397	 * Now the interrupt could also have moved to a different target,
398	 * thus we may need to re-do the ICP lookup as well
399	 */
400
401 again:
402	/* Get the ICS state and lock it */
403	ics = kvmppc_xics_find_ics(xics, new_irq, &src);
404	if (!ics) {
405		XICS_DBG("icp_deliver_irq: IRQ 0x%06x not found !\n", new_irq);
406		return;
407	}
408	state = &ics->irq_state[src];
409
410	/* Get a lock on the ICS */
411	local_irq_save(flags);
412	arch_spin_lock(&ics->lock);
413
414	/* Get our server */
415	if (!icp || state->server != icp->server_num) {
416		icp = kvmppc_xics_find_server(xics->kvm, state->server);
417		if (!icp) {
418			pr_warn("icp_deliver_irq: IRQ 0x%06x server 0x%x not found !\n",
419				new_irq, state->server);
420			goto out;
421		}
422	}
423
424	if (check_resend)
425		if (!state->resend)
426			goto out;
427
428	/* Clear the resend bit of that interrupt */
429	state->resend = 0;
430
431	/*
432	 * If masked, bail out
433	 *
434	 * Note: PAPR doesn't mention anything about masked pending
435	 * when doing a resend, only when doing a delivery.
436	 *
437	 * However that would have the effect of losing a masked
438	 * interrupt that was rejected and isn't consistent with
439	 * the whole masked_pending business which is about not
440	 * losing interrupts that occur while masked.
441	 *
442	 * I don't differentiate normal deliveries and resends, this
443	 * implementation will differ from PAPR and not lose such
444	 * interrupts.
445	 */
446	if (state->priority == MASKED) {
447		XICS_DBG("irq %#x masked pending\n", new_irq);
448		state->masked_pending = 1;
449		goto out;
450	}
451
452	/*
453	 * Try the delivery, this will set the need_resend flag
454	 * in the ICP as part of the atomic transaction if the
455	 * delivery is not possible.
456	 *
457	 * Note that if successful, the new delivery might have itself
458	 * rejected an interrupt that was "delivered" before we took the
459	 * ics spin lock.
460	 *
461	 * In this case we do the whole sequence all over again for the
462	 * new guy. We cannot assume that the rejected interrupt is less
463	 * favored than the new one, and thus doesn't need to be delivered,
464	 * because by the time we exit icp_try_to_deliver() the target
465	 * processor may well have alrady consumed & completed it, and thus
466	 * the rejected interrupt might actually be already acceptable.
467	 */
468	if (icp_try_to_deliver(icp, new_irq, state->priority, &reject)) {
469		/*
470		 * Delivery was successful, did we reject somebody else ?
471		 */
472		if (reject && reject != XICS_IPI) {
473			arch_spin_unlock(&ics->lock);
474			local_irq_restore(flags);
475			new_irq = reject;
476			check_resend = 0;
477			goto again;
478		}
479	} else {
480		/*
481		 * We failed to deliver the interrupt we need to set the
482		 * resend map bit and mark the ICS state as needing a resend
483		 */
484		state->resend = 1;
485
486		/*
487		 * Make sure when checking resend, we don't miss the resend
488		 * if resend_map bit is seen and cleared.
489		 */
490		smp_wmb();
491		set_bit(ics->icsid, icp->resend_map);
492
493		/*
494		 * If the need_resend flag got cleared in the ICP some time
495		 * between icp_try_to_deliver() atomic update and now, then
496		 * we know it might have missed the resend_map bit. So we
497		 * retry
498		 */
499		smp_mb();
500		if (!icp->state.need_resend) {
501			state->resend = 0;
502			arch_spin_unlock(&ics->lock);
503			local_irq_restore(flags);
504			check_resend = 0;
505			goto again;
506		}
507	}
508 out:
509	arch_spin_unlock(&ics->lock);
510	local_irq_restore(flags);
511}
512
513static void icp_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
514			  u8 new_cppr)
515{
516	union kvmppc_icp_state old_state, new_state;
517	bool resend;
518
519	/*
520	 * This handles several related states in one operation:
521	 *
522	 * ICP State: Down_CPPR
523	 *
524	 * Load CPPR with new value and if the XISR is 0
525	 * then check for resends:
526	 *
527	 * ICP State: Resend
528	 *
529	 * If MFRR is more favored than CPPR, check for IPIs
530	 * and notify ICS of a potential resend. This is done
531	 * asynchronously (when used in real mode, we will have
532	 * to exit here).
533	 *
534	 * We do not handle the complete Check_IPI as documented
535	 * here. In the PAPR, this state will be used for both
536	 * Set_MFRR and Down_CPPR. However, we know that we aren't
537	 * changing the MFRR state here so we don't need to handle
538	 * the case of an MFRR causing a reject of a pending irq,
539	 * this will have been handled when the MFRR was set in the
540	 * first place.
541	 *
542	 * Thus we don't have to handle rejects, only resends.
543	 *
544	 * When implementing real mode for HV KVM, resend will lead to
545	 * a H_TOO_HARD return and the whole transaction will be handled
546	 * in virtual mode.
547	 */
548	do {
549		old_state = new_state = READ_ONCE(icp->state);
550
551		/* Down_CPPR */
552		new_state.cppr = new_cppr;
553
554		/*
555		 * Cut down Resend / Check_IPI / IPI
556		 *
557		 * The logic is that we cannot have a pending interrupt
558		 * trumped by an IPI at this point (see above), so we
559		 * know that either the pending interrupt is already an
560		 * IPI (in which case we don't care to override it) or
561		 * it's either more favored than us or non existent
562		 */
563		if (new_state.mfrr < new_cppr &&
564		    new_state.mfrr <= new_state.pending_pri) {
565			WARN_ON(new_state.xisr != XICS_IPI &&
566				new_state.xisr != 0);
567			new_state.pending_pri = new_state.mfrr;
568			new_state.xisr = XICS_IPI;
569		}
570
571		/* Latch/clear resend bit */
572		resend = new_state.need_resend;
573		new_state.need_resend = 0;
574
575	} while (!icp_try_update(icp, old_state, new_state, true));
576
577	/*
578	 * Now handle resend checks. Those are asynchronous to the ICP
579	 * state update in HW (ie bus transactions) so we can handle them
580	 * separately here too
581	 */
582	if (resend)
583		icp_check_resend(xics, icp);
584}
585
586static noinline unsigned long kvmppc_h_xirr(struct kvm_vcpu *vcpu)
587{
588	union kvmppc_icp_state old_state, new_state;
589	struct kvmppc_icp *icp = vcpu->arch.icp;
590	u32 xirr;
591
592	/* First, remove EE from the processor */
593	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
594
595	/*
596	 * ICP State: Accept_Interrupt
597	 *
598	 * Return the pending interrupt (if any) along with the
599	 * current CPPR, then clear the XISR & set CPPR to the
600	 * pending priority
601	 */
602	do {
603		old_state = new_state = READ_ONCE(icp->state);
604
605		xirr = old_state.xisr | (((u32)old_state.cppr) << 24);
606		if (!old_state.xisr)
607			break;
608		new_state.cppr = new_state.pending_pri;
609		new_state.pending_pri = 0xff;
610		new_state.xisr = 0;
611
612	} while (!icp_try_update(icp, old_state, new_state, true));
613
614	XICS_DBG("h_xirr vcpu %d xirr %#x\n", vcpu->vcpu_id, xirr);
615
616	return xirr;
617}
618
619static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
620				 unsigned long mfrr)
621{
622	union kvmppc_icp_state old_state, new_state;
623	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
624	struct kvmppc_icp *icp;
625	u32 reject;
626	bool resend;
627	bool local;
628
629	XICS_DBG("h_ipi vcpu %d to server %lu mfrr %#lx\n",
630		 vcpu->vcpu_id, server, mfrr);
631
632	icp = vcpu->arch.icp;
633	local = icp->server_num == server;
634	if (!local) {
635		icp = kvmppc_xics_find_server(vcpu->kvm, server);
636		if (!icp)
637			return H_PARAMETER;
638	}
639
640	/*
641	 * ICP state: Set_MFRR
642	 *
643	 * If the CPPR is more favored than the new MFRR, then
644	 * nothing needs to be rejected as there can be no XISR to
645	 * reject.  If the MFRR is being made less favored then
646	 * there might be a previously-rejected interrupt needing
647	 * to be resent.
648	 *
649	 * ICP state: Check_IPI
650	 *
651	 * If the CPPR is less favored, then we might be replacing
652	 * an interrupt, and thus need to possibly reject it.
653	 *
654	 * ICP State: IPI
655	 *
656	 * Besides rejecting any pending interrupts, we also
657	 * update XISR and pending_pri to mark IPI as pending.
658	 *
659	 * PAPR does not describe this state, but if the MFRR is being
660	 * made less favored than its earlier value, there might be
661	 * a previously-rejected interrupt needing to be resent.
662	 * Ideally, we would want to resend only if
663	 *	prio(pending_interrupt) < mfrr &&
664	 *	prio(pending_interrupt) < cppr
665	 * where pending interrupt is the one that was rejected. But
666	 * we don't have that state, so we simply trigger a resend
667	 * whenever the MFRR is made less favored.
668	 */
669	do {
670		old_state = new_state = READ_ONCE(icp->state);
671
672		/* Set_MFRR */
673		new_state.mfrr = mfrr;
674
675		/* Check_IPI */
676		reject = 0;
677		resend = false;
678		if (mfrr < new_state.cppr) {
679			/* Reject a pending interrupt if not an IPI */
680			if (mfrr <= new_state.pending_pri) {
681				reject = new_state.xisr;
682				new_state.pending_pri = mfrr;
683				new_state.xisr = XICS_IPI;
684			}
685		}
686
687		if (mfrr > old_state.mfrr) {
688			resend = new_state.need_resend;
689			new_state.need_resend = 0;
690		}
691	} while (!icp_try_update(icp, old_state, new_state, local));
692
693	/* Handle reject */
694	if (reject && reject != XICS_IPI)
695		icp_deliver_irq(xics, icp, reject, false);
696
697	/* Handle resend */
698	if (resend)
699		icp_check_resend(xics, icp);
700
701	return H_SUCCESS;
702}
703
704static int kvmppc_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
705{
706	union kvmppc_icp_state state;
707	struct kvmppc_icp *icp;
708
709	icp = vcpu->arch.icp;
710	if (icp->server_num != server) {
711		icp = kvmppc_xics_find_server(vcpu->kvm, server);
712		if (!icp)
713			return H_PARAMETER;
714	}
715	state = READ_ONCE(icp->state);
716	kvmppc_set_gpr(vcpu, 4, ((u32)state.cppr << 24) | state.xisr);
717	kvmppc_set_gpr(vcpu, 5, state.mfrr);
718	return H_SUCCESS;
719}
720
721static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
722{
723	union kvmppc_icp_state old_state, new_state;
724	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
725	struct kvmppc_icp *icp = vcpu->arch.icp;
726	u32 reject;
727
728	XICS_DBG("h_cppr vcpu %d cppr %#lx\n", vcpu->vcpu_id, cppr);
729
730	/*
731	 * ICP State: Set_CPPR
732	 *
733	 * We can safely compare the new value with the current
734	 * value outside of the transaction as the CPPR is only
735	 * ever changed by the processor on itself
736	 */
737	if (cppr > icp->state.cppr)
738		icp_down_cppr(xics, icp, cppr);
739	else if (cppr == icp->state.cppr)
740		return;
741
742	/*
743	 * ICP State: Up_CPPR
744	 *
745	 * The processor is raising its priority, this can result
746	 * in a rejection of a pending interrupt:
747	 *
748	 * ICP State: Reject_Current
749	 *
750	 * We can remove EE from the current processor, the update
751	 * transaction will set it again if needed
752	 */
753	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
754
755	do {
756		old_state = new_state = READ_ONCE(icp->state);
757
758		reject = 0;
759		new_state.cppr = cppr;
760
761		if (cppr <= new_state.pending_pri) {
762			reject = new_state.xisr;
763			new_state.xisr = 0;
764			new_state.pending_pri = 0xff;
765		}
766
767	} while (!icp_try_update(icp, old_state, new_state, true));
768
769	/*
770	 * Check for rejects. They are handled by doing a new delivery
771	 * attempt (see comments in icp_deliver_irq).
772	 */
773	if (reject && reject != XICS_IPI)
774		icp_deliver_irq(xics, icp, reject, false);
775}
776
777static int ics_eoi(struct kvm_vcpu *vcpu, u32 irq)
778{
779	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
780	struct kvmppc_icp *icp = vcpu->arch.icp;
781	struct kvmppc_ics *ics;
782	struct ics_irq_state *state;
783	u16 src;
784	u32 pq_old, pq_new;
785
786	/*
787	 * ICS EOI handling: For LSI, if P bit is still set, we need to
788	 * resend it.
789	 *
790	 * For MSI, we move Q bit into P (and clear Q). If it is set,
791	 * resend it.
792	 */
793
794	ics = kvmppc_xics_find_ics(xics, irq, &src);
795	if (!ics) {
796		XICS_DBG("ios_eoi: IRQ 0x%06x not found !\n", irq);
797		return H_PARAMETER;
798	}
799	state = &ics->irq_state[src];
800
801	if (state->lsi)
802		pq_new = state->pq_state;
803	else
804		do {
805			pq_old = state->pq_state;
806			pq_new = pq_old >> 1;
807		} while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old);
808
809	if (pq_new & PQ_PRESENTED)
810		icp_deliver_irq(xics, icp, irq, false);
811
812	kvm_notify_acked_irq(vcpu->kvm, 0, irq);
813
814	return H_SUCCESS;
815}
816
817static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
818{
819	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
820	struct kvmppc_icp *icp = vcpu->arch.icp;
821	u32 irq = xirr & 0x00ffffff;
822
823	XICS_DBG("h_eoi vcpu %d eoi %#lx\n", vcpu->vcpu_id, xirr);
824
825	/*
826	 * ICP State: EOI
827	 *
828	 * Note: If EOI is incorrectly used by SW to lower the CPPR
829	 * value (ie more favored), we do not check for rejection of
830	 * a pending interrupt, this is a SW error and PAPR specifies
831	 * that we don't have to deal with it.
832	 *
833	 * The sending of an EOI to the ICS is handled after the
834	 * CPPR update
835	 *
836	 * ICP State: Down_CPPR which we handle
837	 * in a separate function as it's shared with H_CPPR.
838	 */
839	icp_down_cppr(xics, icp, xirr >> 24);
840
841	/* IPIs have no EOI */
842	if (irq == XICS_IPI)
843		return H_SUCCESS;
844
845	return ics_eoi(vcpu, irq);
846}
847
848int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall)
849{
850	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
851	struct kvmppc_icp *icp = vcpu->arch.icp;
852
853	XICS_DBG("XICS_RM: H_%x completing, act: %x state: %lx tgt: %p\n",
854		 hcall, icp->rm_action, icp->rm_dbgstate.raw, icp->rm_dbgtgt);
855
856	if (icp->rm_action & XICS_RM_KICK_VCPU) {
857		icp->n_rm_kick_vcpu++;
858		kvmppc_fast_vcpu_kick(icp->rm_kick_target);
859	}
860	if (icp->rm_action & XICS_RM_CHECK_RESEND) {
861		icp->n_rm_check_resend++;
862		icp_check_resend(xics, icp->rm_resend_icp);
863	}
864	if (icp->rm_action & XICS_RM_NOTIFY_EOI) {
865		icp->n_rm_notify_eoi++;
866		kvm_notify_acked_irq(vcpu->kvm, 0, icp->rm_eoied_irq);
867	}
868
869	icp->rm_action = 0;
870
871	return H_SUCCESS;
872}
873EXPORT_SYMBOL_GPL(kvmppc_xics_rm_complete);
874
875int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
876{
877	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
878	unsigned long res;
879	int rc = H_SUCCESS;
880
881	/* Check if we have an ICP */
882	if (!xics || !vcpu->arch.icp)
883		return H_HARDWARE;
884
885	/* These requests don't have real-mode implementations at present */
886	switch (req) {
887	case H_XIRR_X:
888		res = kvmppc_h_xirr(vcpu);
889		kvmppc_set_gpr(vcpu, 4, res);
890		kvmppc_set_gpr(vcpu, 5, get_tb());
891		return rc;
892	case H_IPOLL:
893		rc = kvmppc_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4));
894		return rc;
895	}
896
897	/* Check for real mode returning too hard */
898	if (xics->real_mode && is_kvmppc_hv_enabled(vcpu->kvm))
899		return kvmppc_xics_rm_complete(vcpu, req);
900
901	switch (req) {
902	case H_XIRR:
903		res = kvmppc_h_xirr(vcpu);
904		kvmppc_set_gpr(vcpu, 4, res);
905		break;
906	case H_CPPR:
907		kvmppc_h_cppr(vcpu, kvmppc_get_gpr(vcpu, 4));
908		break;
909	case H_EOI:
910		rc = kvmppc_h_eoi(vcpu, kvmppc_get_gpr(vcpu, 4));
911		break;
912	case H_IPI:
913		rc = kvmppc_h_ipi(vcpu, kvmppc_get_gpr(vcpu, 4),
914				  kvmppc_get_gpr(vcpu, 5));
915		break;
916	}
917
918	return rc;
919}
920EXPORT_SYMBOL_GPL(kvmppc_xics_hcall);
921
922
923/* -- Initialisation code etc. -- */
924
925static void xics_debugfs_irqmap(struct seq_file *m,
926				struct kvmppc_passthru_irqmap *pimap)
927{
928	int i;
929
930	if (!pimap)
931		return;
932	seq_printf(m, "========\nPIRQ mappings: %d maps\n===========\n",
933				pimap->n_mapped);
934	for (i = 0; i < pimap->n_mapped; i++)  {
935		seq_printf(m, "r_hwirq=%x, v_hwirq=%x\n",
936			pimap->mapped[i].r_hwirq, pimap->mapped[i].v_hwirq);
937	}
938}
939
940static int xics_debug_show(struct seq_file *m, void *private)
941{
942	struct kvmppc_xics *xics = m->private;
943	struct kvm *kvm = xics->kvm;
944	struct kvm_vcpu *vcpu;
945	int icsid, i;
946	unsigned long flags;
947	unsigned long t_rm_kick_vcpu, t_rm_check_resend;
948	unsigned long t_rm_notify_eoi;
949	unsigned long t_reject, t_check_resend;
950
951	if (!kvm)
952		return 0;
953
954	t_rm_kick_vcpu = 0;
955	t_rm_notify_eoi = 0;
956	t_rm_check_resend = 0;
957	t_check_resend = 0;
958	t_reject = 0;
959
960	xics_debugfs_irqmap(m, kvm->arch.pimap);
961
962	seq_printf(m, "=========\nICP state\n=========\n");
963
964	kvm_for_each_vcpu(i, vcpu, kvm) {
965		struct kvmppc_icp *icp = vcpu->arch.icp;
966		union kvmppc_icp_state state;
967
968		if (!icp)
969			continue;
970
971		state.raw = READ_ONCE(icp->state.raw);
972		seq_printf(m, "cpu server %#lx XIRR:%#x PPRI:%#x CPPR:%#x MFRR:%#x OUT:%d NR:%d\n",
973			   icp->server_num, state.xisr,
974			   state.pending_pri, state.cppr, state.mfrr,
975			   state.out_ee, state.need_resend);
976		t_rm_kick_vcpu += icp->n_rm_kick_vcpu;
977		t_rm_notify_eoi += icp->n_rm_notify_eoi;
978		t_rm_check_resend += icp->n_rm_check_resend;
979		t_check_resend += icp->n_check_resend;
980		t_reject += icp->n_reject;
981	}
982
983	seq_printf(m, "ICP Guest->Host totals: kick_vcpu=%lu check_resend=%lu notify_eoi=%lu\n",
984			t_rm_kick_vcpu, t_rm_check_resend,
985			t_rm_notify_eoi);
986	seq_printf(m, "ICP Real Mode totals: check_resend=%lu resend=%lu\n",
987			t_check_resend, t_reject);
988	for (icsid = 0; icsid <= KVMPPC_XICS_MAX_ICS_ID; icsid++) {
989		struct kvmppc_ics *ics = xics->ics[icsid];
990
991		if (!ics)
992			continue;
993
994		seq_printf(m, "=========\nICS state for ICS 0x%x\n=========\n",
995			   icsid);
996
997		local_irq_save(flags);
998		arch_spin_lock(&ics->lock);
999
1000		for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
1001			struct ics_irq_state *irq = &ics->irq_state[i];
1002
1003			seq_printf(m, "irq 0x%06x: server %#x prio %#x save prio %#x pq_state %d resend %d masked pending %d\n",
1004				   irq->number, irq->server, irq->priority,
1005				   irq->saved_priority, irq->pq_state,
1006				   irq->resend, irq->masked_pending);
1007
1008		}
1009		arch_spin_unlock(&ics->lock);
1010		local_irq_restore(flags);
1011	}
1012	return 0;
1013}
1014
1015DEFINE_SHOW_ATTRIBUTE(xics_debug);
1016
1017static void xics_debugfs_init(struct kvmppc_xics *xics)
1018{
1019	char *name;
1020
1021	name = kasprintf(GFP_KERNEL, "kvm-xics-%p", xics);
1022	if (!name) {
1023		pr_err("%s: no memory for name\n", __func__);
1024		return;
1025	}
1026
1027	xics->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root,
1028					   xics, &xics_debug_fops);
1029
1030	pr_debug("%s: created %s\n", __func__, name);
1031	kfree(name);
1032}
1033
1034static struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm,
1035					struct kvmppc_xics *xics, int irq)
1036{
1037	struct kvmppc_ics *ics;
1038	int i, icsid;
1039
1040	icsid = irq >> KVMPPC_XICS_ICS_SHIFT;
1041
1042	mutex_lock(&kvm->lock);
1043
1044	/* ICS already exists - somebody else got here first */
1045	if (xics->ics[icsid])
1046		goto out;
1047
1048	/* Create the ICS */
1049	ics = kzalloc(sizeof(struct kvmppc_ics), GFP_KERNEL);
1050	if (!ics)
1051		goto out;
1052
1053	ics->icsid = icsid;
1054
1055	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
1056		ics->irq_state[i].number = (icsid << KVMPPC_XICS_ICS_SHIFT) | i;
1057		ics->irq_state[i].priority = MASKED;
1058		ics->irq_state[i].saved_priority = MASKED;
1059	}
1060	smp_wmb();
1061	xics->ics[icsid] = ics;
1062
1063	if (icsid > xics->max_icsid)
1064		xics->max_icsid = icsid;
1065
1066 out:
1067	mutex_unlock(&kvm->lock);
1068	return xics->ics[icsid];
1069}
1070
1071static int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server_num)
1072{
1073	struct kvmppc_icp *icp;
1074
1075	if (!vcpu->kvm->arch.xics)
1076		return -ENODEV;
1077
1078	if (kvmppc_xics_find_server(vcpu->kvm, server_num))
1079		return -EEXIST;
1080
1081	icp = kzalloc(sizeof(struct kvmppc_icp), GFP_KERNEL);
1082	if (!icp)
1083		return -ENOMEM;
1084
1085	icp->vcpu = vcpu;
1086	icp->server_num = server_num;
1087	icp->state.mfrr = MASKED;
1088	icp->state.pending_pri = MASKED;
1089	vcpu->arch.icp = icp;
1090
1091	XICS_DBG("created server for vcpu %d\n", vcpu->vcpu_id);
1092
1093	return 0;
1094}
1095
1096u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu)
1097{
1098	struct kvmppc_icp *icp = vcpu->arch.icp;
1099	union kvmppc_icp_state state;
1100
1101	if (!icp)
1102		return 0;
1103	state = icp->state;
1104	return ((u64)state.cppr << KVM_REG_PPC_ICP_CPPR_SHIFT) |
1105		((u64)state.xisr << KVM_REG_PPC_ICP_XISR_SHIFT) |
1106		((u64)state.mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT) |
1107		((u64)state.pending_pri << KVM_REG_PPC_ICP_PPRI_SHIFT);
1108}
1109
1110int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
1111{
1112	struct kvmppc_icp *icp = vcpu->arch.icp;
1113	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
1114	union kvmppc_icp_state old_state, new_state;
1115	struct kvmppc_ics *ics;
1116	u8 cppr, mfrr, pending_pri;
1117	u32 xisr;
1118	u16 src;
1119	bool resend;
1120
1121	if (!icp || !xics)
1122		return -ENOENT;
1123
1124	cppr = icpval >> KVM_REG_PPC_ICP_CPPR_SHIFT;
1125	xisr = (icpval >> KVM_REG_PPC_ICP_XISR_SHIFT) &
1126		KVM_REG_PPC_ICP_XISR_MASK;
1127	mfrr = icpval >> KVM_REG_PPC_ICP_MFRR_SHIFT;
1128	pending_pri = icpval >> KVM_REG_PPC_ICP_PPRI_SHIFT;
1129
1130	/* Require the new state to be internally consistent */
1131	if (xisr == 0) {
1132		if (pending_pri != 0xff)
1133			return -EINVAL;
1134	} else if (xisr == XICS_IPI) {
1135		if (pending_pri != mfrr || pending_pri >= cppr)
1136			return -EINVAL;
1137	} else {
1138		if (pending_pri >= mfrr || pending_pri >= cppr)
1139			return -EINVAL;
1140		ics = kvmppc_xics_find_ics(xics, xisr, &src);
1141		if (!ics)
1142			return -EINVAL;
1143	}
1144
1145	new_state.raw = 0;
1146	new_state.cppr = cppr;
1147	new_state.xisr = xisr;
1148	new_state.mfrr = mfrr;
1149	new_state.pending_pri = pending_pri;
1150
1151	/*
1152	 * Deassert the CPU interrupt request.
1153	 * icp_try_update will reassert it if necessary.
1154	 */
1155	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
1156
1157	/*
1158	 * Note that if we displace an interrupt from old_state.xisr,
1159	 * we don't mark it as rejected.  We expect userspace to set
1160	 * the state of the interrupt sources to be consistent with
1161	 * the ICP states (either before or afterwards, which doesn't
1162	 * matter).  We do handle resends due to CPPR becoming less
1163	 * favoured because that is necessary to end up with a
1164	 * consistent state in the situation where userspace restores
1165	 * the ICS states before the ICP states.
1166	 */
1167	do {
1168		old_state = READ_ONCE(icp->state);
1169
1170		if (new_state.mfrr <= old_state.mfrr) {
1171			resend = false;
1172			new_state.need_resend = old_state.need_resend;
1173		} else {
1174			resend = old_state.need_resend;
1175			new_state.need_resend = 0;
1176		}
1177	} while (!icp_try_update(icp, old_state, new_state, false));
1178
1179	if (resend)
1180		icp_check_resend(xics, icp);
1181
1182	return 0;
1183}
1184
1185static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr)
1186{
1187	int ret;
1188	struct kvmppc_ics *ics;
1189	struct ics_irq_state *irqp;
1190	u64 __user *ubufp = (u64 __user *) addr;
1191	u16 idx;
1192	u64 val, prio;
1193	unsigned long flags;
1194
1195	ics = kvmppc_xics_find_ics(xics, irq, &idx);
1196	if (!ics)
1197		return -ENOENT;
1198
1199	irqp = &ics->irq_state[idx];
1200	local_irq_save(flags);
1201	arch_spin_lock(&ics->lock);
1202	ret = -ENOENT;
1203	if (irqp->exists) {
1204		val = irqp->server;
1205		prio = irqp->priority;
1206		if (prio == MASKED) {
1207			val |= KVM_XICS_MASKED;
1208			prio = irqp->saved_priority;
1209		}
1210		val |= prio << KVM_XICS_PRIORITY_SHIFT;
1211		if (irqp->lsi) {
1212			val |= KVM_XICS_LEVEL_SENSITIVE;
1213			if (irqp->pq_state & PQ_PRESENTED)
1214				val |= KVM_XICS_PENDING;
1215		} else if (irqp->masked_pending || irqp->resend)
1216			val |= KVM_XICS_PENDING;
1217
1218		if (irqp->pq_state & PQ_PRESENTED)
1219			val |= KVM_XICS_PRESENTED;
1220
1221		if (irqp->pq_state & PQ_QUEUED)
1222			val |= KVM_XICS_QUEUED;
1223
1224		ret = 0;
1225	}
1226	arch_spin_unlock(&ics->lock);
1227	local_irq_restore(flags);
1228
1229	if (!ret && put_user(val, ubufp))
1230		ret = -EFAULT;
1231
1232	return ret;
1233}
1234
1235static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr)
1236{
1237	struct kvmppc_ics *ics;
1238	struct ics_irq_state *irqp;
1239	u64 __user *ubufp = (u64 __user *) addr;
1240	u16 idx;
1241	u64 val;
1242	u8 prio;
1243	u32 server;
1244	unsigned long flags;
1245
1246	if (irq < KVMPPC_XICS_FIRST_IRQ || irq >= KVMPPC_XICS_NR_IRQS)
1247		return -ENOENT;
1248
1249	ics = kvmppc_xics_find_ics(xics, irq, &idx);
1250	if (!ics) {
1251		ics = kvmppc_xics_create_ics(xics->kvm, xics, irq);
1252		if (!ics)
1253			return -ENOMEM;
1254	}
1255	irqp = &ics->irq_state[idx];
1256	if (get_user(val, ubufp))
1257		return -EFAULT;
1258
1259	server = val & KVM_XICS_DESTINATION_MASK;
1260	prio = val >> KVM_XICS_PRIORITY_SHIFT;
1261	if (prio != MASKED &&
1262	    kvmppc_xics_find_server(xics->kvm, server) == NULL)
1263		return -EINVAL;
1264
1265	local_irq_save(flags);
1266	arch_spin_lock(&ics->lock);
1267	irqp->server = server;
1268	irqp->saved_priority = prio;
1269	if (val & KVM_XICS_MASKED)
1270		prio = MASKED;
1271	irqp->priority = prio;
1272	irqp->resend = 0;
1273	irqp->masked_pending = 0;
1274	irqp->lsi = 0;
1275	irqp->pq_state = 0;
1276	if (val & KVM_XICS_LEVEL_SENSITIVE)
1277		irqp->lsi = 1;
1278	/* If PENDING, set P in case P is not saved because of old code */
1279	if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
1280		irqp->pq_state |= PQ_PRESENTED;
1281	if (val & KVM_XICS_QUEUED)
1282		irqp->pq_state |= PQ_QUEUED;
1283	irqp->exists = 1;
1284	arch_spin_unlock(&ics->lock);
1285	local_irq_restore(flags);
1286
1287	if (val & KVM_XICS_PENDING)
1288		icp_deliver_irq(xics, NULL, irqp->number, false);
1289
1290	return 0;
1291}
1292
1293int kvmppc_xics_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
1294			bool line_status)
1295{
1296	struct kvmppc_xics *xics = kvm->arch.xics;
1297
1298	if (!xics)
1299		return -ENODEV;
1300	return ics_deliver_irq(xics, irq, level);
1301}
1302
1303static int xics_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
1304{
1305	struct kvmppc_xics *xics = dev->private;
1306
1307	switch (attr->group) {
1308	case KVM_DEV_XICS_GRP_SOURCES:
1309		return xics_set_source(xics, attr->attr, attr->addr);
1310	}
1311	return -ENXIO;
1312}
1313
1314static int xics_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
1315{
1316	struct kvmppc_xics *xics = dev->private;
1317
1318	switch (attr->group) {
1319	case KVM_DEV_XICS_GRP_SOURCES:
1320		return xics_get_source(xics, attr->attr, attr->addr);
1321	}
1322	return -ENXIO;
1323}
1324
1325static int xics_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
1326{
1327	switch (attr->group) {
1328	case KVM_DEV_XICS_GRP_SOURCES:
1329		if (attr->attr >= KVMPPC_XICS_FIRST_IRQ &&
1330		    attr->attr < KVMPPC_XICS_NR_IRQS)
1331			return 0;
1332		break;
1333	}
1334	return -ENXIO;
1335}
1336
1337/*
1338 * Called when device fd is closed. kvm->lock is held.
1339 */
1340static void kvmppc_xics_release(struct kvm_device *dev)
1341{
1342	struct kvmppc_xics *xics = dev->private;
1343	int i;
1344	struct kvm *kvm = xics->kvm;
1345	struct kvm_vcpu *vcpu;
1346
1347	pr_devel("Releasing xics device\n");
1348
1349	/*
1350	 * Since this is the device release function, we know that
1351	 * userspace does not have any open fd referring to the
1352	 * device.  Therefore there can not be any of the device
1353	 * attribute set/get functions being executed concurrently,
1354	 * and similarly, the connect_vcpu and set/clr_mapped
1355	 * functions also cannot be being executed.
1356	 */
1357
1358	debugfs_remove(xics->dentry);
1359
1360	/*
1361	 * We should clean up the vCPU interrupt presenters first.
1362	 */
1363	kvm_for_each_vcpu(i, vcpu, kvm) {
1364		/*
1365		 * Take vcpu->mutex to ensure that no one_reg get/set ioctl
1366		 * (i.e. kvmppc_xics_[gs]et_icp) can be done concurrently.
1367		 * Holding the vcpu->mutex also means that execution is
1368		 * excluded for the vcpu until the ICP was freed. When the vcpu
1369		 * can execute again, vcpu->arch.icp and vcpu->arch.irq_type
1370		 * have been cleared and the vcpu will not be going into the
1371		 * XICS code anymore.
1372		 */
1373		mutex_lock(&vcpu->mutex);
1374		kvmppc_xics_free_icp(vcpu);
1375		mutex_unlock(&vcpu->mutex);
1376	}
1377
1378	if (kvm)
1379		kvm->arch.xics = NULL;
1380
1381	for (i = 0; i <= xics->max_icsid; i++) {
1382		kfree(xics->ics[i]);
1383		xics->ics[i] = NULL;
1384	}
1385	/*
1386	 * A reference of the kvmppc_xics pointer is now kept under
1387	 * the xics_device pointer of the machine for reuse. It is
1388	 * freed when the VM is destroyed for now until we fix all the
1389	 * execution paths.
1390	 */
1391	kfree(dev);
1392}
1393
1394static struct kvmppc_xics *kvmppc_xics_get_device(struct kvm *kvm)
1395{
1396	struct kvmppc_xics **kvm_xics_device = &kvm->arch.xics_device;
1397	struct kvmppc_xics *xics = *kvm_xics_device;
1398
1399	if (!xics) {
1400		xics = kzalloc(sizeof(*xics), GFP_KERNEL);
1401		*kvm_xics_device = xics;
1402	} else {
1403		memset(xics, 0, sizeof(*xics));
1404	}
1405
1406	return xics;
1407}
1408
1409static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
1410{
1411	struct kvmppc_xics *xics;
1412	struct kvm *kvm = dev->kvm;
1413
1414	pr_devel("Creating xics for partition\n");
1415
1416	/* Already there ? */
1417	if (kvm->arch.xics)
1418		return -EEXIST;
1419
1420	xics = kvmppc_xics_get_device(kvm);
1421	if (!xics)
1422		return -ENOMEM;
1423
1424	dev->private = xics;
1425	xics->dev = dev;
1426	xics->kvm = kvm;
1427	kvm->arch.xics = xics;
1428
1429#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
1430	if (cpu_has_feature(CPU_FTR_ARCH_206) &&
1431	    cpu_has_feature(CPU_FTR_HVMODE)) {
1432		/* Enable real mode support */
1433		xics->real_mode = ENABLE_REALMODE;
1434		xics->real_mode_dbg = DEBUG_REALMODE;
1435	}
1436#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
1437
1438	return 0;
1439}
1440
1441static void kvmppc_xics_init(struct kvm_device *dev)
1442{
1443	struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private;
1444
1445	xics_debugfs_init(xics);
1446}
1447
1448struct kvm_device_ops kvm_xics_ops = {
1449	.name = "kvm-xics",
1450	.create = kvmppc_xics_create,
1451	.init = kvmppc_xics_init,
1452	.release = kvmppc_xics_release,
1453	.set_attr = xics_set_attr,
1454	.get_attr = xics_get_attr,
1455	.has_attr = xics_has_attr,
1456};
1457
1458int kvmppc_xics_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu,
1459			     u32 xcpu)
1460{
1461	struct kvmppc_xics *xics = dev->private;
1462	int r = -EBUSY;
1463
1464	if (dev->ops != &kvm_xics_ops)
1465		return -EPERM;
1466	if (xics->kvm != vcpu->kvm)
1467		return -EPERM;
1468	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
1469		return -EBUSY;
1470
1471	r = kvmppc_xics_create_icp(vcpu, xcpu);
1472	if (!r)
1473		vcpu->arch.irq_type = KVMPPC_IRQ_XICS;
1474
1475	return r;
1476}
1477
1478void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu)
1479{
1480	if (!vcpu->arch.icp)
1481		return;
1482	kfree(vcpu->arch.icp);
1483	vcpu->arch.icp = NULL;
1484	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
1485}
1486
1487void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long irq,
1488			    unsigned long host_irq)
1489{
1490	struct kvmppc_xics *xics = kvm->arch.xics;
1491	struct kvmppc_ics *ics;
1492	u16 idx;
1493
1494	ics = kvmppc_xics_find_ics(xics, irq, &idx);
1495	if (!ics)
1496		return;
1497
1498	ics->irq_state[idx].host_irq = host_irq;
1499	ics->irq_state[idx].intr_cpu = -1;
1500}
1501EXPORT_SYMBOL_GPL(kvmppc_xics_set_mapped);
1502
1503void kvmppc_xics_clr_mapped(struct kvm *kvm, unsigned long irq,
1504			    unsigned long host_irq)
1505{
1506	struct kvmppc_xics *xics = kvm->arch.xics;
1507	struct kvmppc_ics *ics;
1508	u16 idx;
1509
1510	ics = kvmppc_xics_find_ics(xics, irq, &idx);
1511	if (!ics)
1512		return;
1513
1514	ics->irq_state[idx].host_irq = 0;
1515}
1516EXPORT_SYMBOL_GPL(kvmppc_xics_clr_mapped);
1517