1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
4 * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
5 *
6 * Authors:
7 *    Paul Mackerras <paulus@au1.ibm.com>
8 *    Alexander Graf <agraf@suse.de>
9 *    Kevin Wolf <mail@kevin-wolf.de>
10 *
11 * Description: KVM functions specific to running on Book 3S
12 * processors in hypervisor mode (specifically POWER7 and later).
13 *
14 * This file is derived from arch/powerpc/kvm/book3s.c,
15 * by Alexander Graf <agraf@suse.de>.
16 */
17
18#include <linux/kvm_host.h>
19#include <linux/kernel.h>
20#include <linux/err.h>
21#include <linux/slab.h>
22#include <linux/preempt.h>
23#include <linux/sched/signal.h>
24#include <linux/sched/stat.h>
25#include <linux/delay.h>
26#include <linux/export.h>
27#include <linux/fs.h>
28#include <linux/anon_inodes.h>
29#include <linux/cpu.h>
30#include <linux/cpumask.h>
31#include <linux/spinlock.h>
32#include <linux/page-flags.h>
33#include <linux/srcu.h>
34#include <linux/miscdevice.h>
35#include <linux/debugfs.h>
36#include <linux/gfp.h>
37#include <linux/vmalloc.h>
38#include <linux/highmem.h>
39#include <linux/hugetlb.h>
40#include <linux/kvm_irqfd.h>
41#include <linux/irqbypass.h>
42#include <linux/module.h>
43#include <linux/compiler.h>
44#include <linux/of.h>
45
46#include <asm/ftrace.h>
47#include <asm/reg.h>
48#include <asm/ppc-opcode.h>
49#include <asm/asm-prototypes.h>
50#include <asm/archrandom.h>
51#include <asm/debug.h>
52#include <asm/disassemble.h>
53#include <asm/cputable.h>
54#include <asm/cacheflush.h>
55#include <linux/uaccess.h>
56#include <asm/io.h>
57#include <asm/kvm_ppc.h>
58#include <asm/kvm_book3s.h>
59#include <asm/mmu_context.h>
60#include <asm/lppaca.h>
61#include <asm/pmc.h>
62#include <asm/processor.h>
63#include <asm/cputhreads.h>
64#include <asm/page.h>
65#include <asm/hvcall.h>
66#include <asm/switch_to.h>
67#include <asm/smp.h>
68#include <asm/dbell.h>
69#include <asm/hmi.h>
70#include <asm/pnv-pci.h>
71#include <asm/mmu.h>
72#include <asm/opal.h>
73#include <asm/xics.h>
74#include <asm/xive.h>
75#include <asm/hw_breakpoint.h>
76#include <asm/kvm_book3s_uvmem.h>
77#include <asm/ultravisor.h>
78#include <asm/dtl.h>
79
80#include "book3s.h"
81
82#define CREATE_TRACE_POINTS
83#include "trace_hv.h"
84
85/* #define EXIT_DEBUG */
86/* #define EXIT_DEBUG_SIMPLE */
87/* #define EXIT_DEBUG_INT */
88
89/* Used to indicate that a guest page fault needs to be handled */
90#define RESUME_PAGE_FAULT	(RESUME_GUEST | RESUME_FLAG_ARCH1)
91/* Used to indicate that a guest passthrough interrupt needs to be handled */
92#define RESUME_PASSTHROUGH	(RESUME_GUEST | RESUME_FLAG_ARCH2)
93
94/* Used as a "null" value for timebase values */
95#define TB_NIL	(~(u64)0)
96
97static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
98
99static int dynamic_mt_modes = 6;
100module_param(dynamic_mt_modes, int, 0644);
101MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes: 0 (= none), 2, 4, or 6 (= 2 or 4)");
102static int target_smt_mode;
103module_param(target_smt_mode, int, 0644);
104MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
105
106static bool indep_threads_mode = true;
107module_param(indep_threads_mode, bool, S_IRUGO | S_IWUSR);
108MODULE_PARM_DESC(indep_threads_mode, "Independent-threads mode (only on POWER9)");
109
110static bool one_vm_per_core;
111module_param(one_vm_per_core, bool, S_IRUGO | S_IWUSR);
112MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires indep_threads_mode=N)");
113
114#ifdef CONFIG_KVM_XICS
115static const struct kernel_param_ops module_param_ops = {
116	.set = param_set_int,
117	.get = param_get_int,
118};
119
120module_param_cb(kvm_irq_bypass, &module_param_ops, &kvm_irq_bypass, 0644);
121MODULE_PARM_DESC(kvm_irq_bypass, "Bypass passthrough interrupt optimization");
122
123module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect, 0644);
124MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
125#endif
126
127/* If set, guests are allowed to create and control nested guests */
128static bool nested = true;
129module_param(nested, bool, S_IRUGO | S_IWUSR);
130MODULE_PARM_DESC(nested, "Enable nested virtualization (only on POWER9)");
131
132static inline bool nesting_enabled(struct kvm *kvm)
133{
134	return kvm->arch.nested_enable && kvm_is_radix(kvm);
135}
136
137/* If set, the threads on each CPU core have to be in the same MMU mode */
138static bool no_mixing_hpt_and_radix;
139
140static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
141
142/*
143 * RWMR values for POWER8.  These control the rate at which PURR
144 * and SPURR count and should be set according to the number of
145 * online threads in the vcore being run.
146 */
147#define RWMR_RPA_P8_1THREAD	0x164520C62609AECAUL
148#define RWMR_RPA_P8_2THREAD	0x7FFF2908450D8DA9UL
149#define RWMR_RPA_P8_3THREAD	0x164520C62609AECAUL
150#define RWMR_RPA_P8_4THREAD	0x199A421245058DA9UL
151#define RWMR_RPA_P8_5THREAD	0x164520C62609AECAUL
152#define RWMR_RPA_P8_6THREAD	0x164520C62609AECAUL
153#define RWMR_RPA_P8_7THREAD	0x164520C62609AECAUL
154#define RWMR_RPA_P8_8THREAD	0x164520C62609AECAUL
155
156static unsigned long p8_rwmr_values[MAX_SMT_THREADS + 1] = {
157	RWMR_RPA_P8_1THREAD,
158	RWMR_RPA_P8_1THREAD,
159	RWMR_RPA_P8_2THREAD,
160	RWMR_RPA_P8_3THREAD,
161	RWMR_RPA_P8_4THREAD,
162	RWMR_RPA_P8_5THREAD,
163	RWMR_RPA_P8_6THREAD,
164	RWMR_RPA_P8_7THREAD,
165	RWMR_RPA_P8_8THREAD,
166};
167
168static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
169		int *ip)
170{
171	int i = *ip;
172	struct kvm_vcpu *vcpu;
173
174	while (++i < MAX_SMT_THREADS) {
175		vcpu = READ_ONCE(vc->runnable_threads[i]);
176		if (vcpu) {
177			*ip = i;
178			return vcpu;
179		}
180	}
181	return NULL;
182}
183
184/* Used to traverse the list of runnable threads for a given vcore */
185#define for_each_runnable_thread(i, vcpu, vc) \
186	for (i = -1; (vcpu = next_runnable_thread(vc, &i)); )
187
188static bool kvmppc_ipi_thread(int cpu)
189{
190	unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
191
192	/* If we're a nested hypervisor, fall back to ordinary IPIs for now */
193	if (kvmhv_on_pseries())
194		return false;
195
196	/* On POWER9 we can use msgsnd to IPI any cpu */
197	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
198		msg |= get_hard_smp_processor_id(cpu);
199		smp_mb();
200		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
201		return true;
202	}
203
204	/* On POWER8 for IPIs to threads in the same core, use msgsnd */
205	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
206		preempt_disable();
207		if (cpu_first_thread_sibling(cpu) ==
208		    cpu_first_thread_sibling(smp_processor_id())) {
209			msg |= cpu_thread_in_core(cpu);
210			smp_mb();
211			__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
212			preempt_enable();
213			return true;
214		}
215		preempt_enable();
216	}
217
218#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
219	if (cpu >= 0 && cpu < nr_cpu_ids) {
220		if (paca_ptrs[cpu]->kvm_hstate.xics_phys) {
221			xics_wake_cpu(cpu);
222			return true;
223		}
224		opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY);
225		return true;
226	}
227#endif
228
229	return false;
230}
231
232static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
233{
234	int cpu;
235	struct rcuwait *waitp;
236
237	waitp = kvm_arch_vcpu_get_wait(vcpu);
238	if (rcuwait_wake_up(waitp))
239		++vcpu->stat.halt_wakeup;
240
241	cpu = READ_ONCE(vcpu->arch.thread_cpu);
242	if (cpu >= 0 && kvmppc_ipi_thread(cpu))
243		return;
244
245	/* CPU points to the first thread of the core */
246	cpu = vcpu->cpu;
247	if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
248		smp_send_reschedule(cpu);
249}
250
251/*
252 * We use the vcpu_load/put functions to measure stolen time.
253 * Stolen time is counted as time when either the vcpu is able to
254 * run as part of a virtual core, but the task running the vcore
255 * is preempted or sleeping, or when the vcpu needs something done
256 * in the kernel by the task running the vcpu, but that task is
257 * preempted or sleeping.  Those two things have to be counted
258 * separately, since one of the vcpu tasks will take on the job
259 * of running the core, and the other vcpu tasks in the vcore will
260 * sleep waiting for it to do that, but that sleep shouldn't count
261 * as stolen time.
262 *
263 * Hence we accumulate stolen time when the vcpu can run as part of
264 * a vcore using vc->stolen_tb, and the stolen time when the vcpu
265 * needs its task to do other things in the kernel (for example,
266 * service a page fault) in busy_stolen.  We don't accumulate
267 * stolen time for a vcore when it is inactive, or for a vcpu
268 * when it is in state RUNNING or NOTREADY.  NOTREADY is a bit of
269 * a misnomer; it means that the vcpu task is not executing in
270 * the KVM_VCPU_RUN ioctl, i.e. it is in userspace or elsewhere in
271 * the kernel.  We don't have any way of dividing up that time
272 * between time that the vcpu is genuinely stopped, time that
273 * the task is actively working on behalf of the vcpu, and time
274 * that the task is preempted, so we don't count any of it as
275 * stolen.
276 *
277 * Updates to busy_stolen are protected by arch.tbacct_lock;
278 * updates to vc->stolen_tb are protected by the vcore->stoltb_lock
279 * lock.  The stolen times are measured in units of timebase ticks.
280 * (Note that the != TB_NIL checks below are purely defensive;
281 * they should never fail.)
282 */
283
284static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc)
285{
286	unsigned long flags;
287
288	spin_lock_irqsave(&vc->stoltb_lock, flags);
289	vc->preempt_tb = mftb();
290	spin_unlock_irqrestore(&vc->stoltb_lock, flags);
291}
292
293static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc)
294{
295	unsigned long flags;
296
297	spin_lock_irqsave(&vc->stoltb_lock, flags);
298	if (vc->preempt_tb != TB_NIL) {
299		vc->stolen_tb += mftb() - vc->preempt_tb;
300		vc->preempt_tb = TB_NIL;
301	}
302	spin_unlock_irqrestore(&vc->stoltb_lock, flags);
303}
304
305static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
306{
307	struct kvmppc_vcore *vc = vcpu->arch.vcore;
308	unsigned long flags;
309
310	/*
311	 * We can test vc->runner without taking the vcore lock,
312	 * because only this task ever sets vc->runner to this
313	 * vcpu, and once it is set to this vcpu, only this task
314	 * ever sets it to NULL.
315	 */
316	if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING)
317		kvmppc_core_end_stolen(vc);
318
319	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
320	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST &&
321	    vcpu->arch.busy_preempt != TB_NIL) {
322		vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
323		vcpu->arch.busy_preempt = TB_NIL;
324	}
325	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
326}
327
328static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
329{
330	struct kvmppc_vcore *vc = vcpu->arch.vcore;
331	unsigned long flags;
332
333	if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING)
334		kvmppc_core_start_stolen(vc);
335
336	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
337	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
338		vcpu->arch.busy_preempt = mftb();
339	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
340}
341
342static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
343{
344	vcpu->arch.pvr = pvr;
345}
346
347/* Dummy value used in computing PCR value below */
348#define PCR_ARCH_31    (PCR_ARCH_300 << 1)
349
350static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
351{
352	unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
353	struct kvmppc_vcore *vc = vcpu->arch.vcore;
354
355	/* We can (emulate) our own architecture version and anything older */
356	if (cpu_has_feature(CPU_FTR_ARCH_31))
357		host_pcr_bit = PCR_ARCH_31;
358	else if (cpu_has_feature(CPU_FTR_ARCH_300))
359		host_pcr_bit = PCR_ARCH_300;
360	else if (cpu_has_feature(CPU_FTR_ARCH_207S))
361		host_pcr_bit = PCR_ARCH_207;
362	else if (cpu_has_feature(CPU_FTR_ARCH_206))
363		host_pcr_bit = PCR_ARCH_206;
364	else
365		host_pcr_bit = PCR_ARCH_205;
366
367	/* Determine lowest PCR bit needed to run guest in given PVR level */
368	guest_pcr_bit = host_pcr_bit;
369	if (arch_compat) {
370		switch (arch_compat) {
371		case PVR_ARCH_205:
372			guest_pcr_bit = PCR_ARCH_205;
373			break;
374		case PVR_ARCH_206:
375		case PVR_ARCH_206p:
376			guest_pcr_bit = PCR_ARCH_206;
377			break;
378		case PVR_ARCH_207:
379			guest_pcr_bit = PCR_ARCH_207;
380			break;
381		case PVR_ARCH_300:
382			guest_pcr_bit = PCR_ARCH_300;
383			break;
384		case PVR_ARCH_31:
385			guest_pcr_bit = PCR_ARCH_31;
386			break;
387		default:
388			return -EINVAL;
389		}
390	}
391
392	/* Check requested PCR bits don't exceed our capabilities */
393	if (guest_pcr_bit > host_pcr_bit)
394		return -EINVAL;
395
396	spin_lock(&vc->lock);
397	vc->arch_compat = arch_compat;
398	/*
399	 * Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit
400	 * Also set all reserved PCR bits
401	 */
402	vc->pcr = (host_pcr_bit - guest_pcr_bit) | PCR_MASK;
403	spin_unlock(&vc->lock);
404
405	return 0;
406}
407
408static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
409{
410	int r;
411
412	pr_err("vcpu %p (%d):\n", vcpu, vcpu->vcpu_id);
413	pr_err("pc  = %.16lx  msr = %.16llx  trap = %x\n",
414	       vcpu->arch.regs.nip, vcpu->arch.shregs.msr, vcpu->arch.trap);
415	for (r = 0; r < 16; ++r)
416		pr_err("r%2d = %.16lx  r%d = %.16lx\n",
417		       r, kvmppc_get_gpr(vcpu, r),
418		       r+16, kvmppc_get_gpr(vcpu, r+16));
419	pr_err("ctr = %.16lx  lr  = %.16lx\n",
420	       vcpu->arch.regs.ctr, vcpu->arch.regs.link);
421	pr_err("srr0 = %.16llx srr1 = %.16llx\n",
422	       vcpu->arch.shregs.srr0, vcpu->arch.shregs.srr1);
423	pr_err("sprg0 = %.16llx sprg1 = %.16llx\n",
424	       vcpu->arch.shregs.sprg0, vcpu->arch.shregs.sprg1);
425	pr_err("sprg2 = %.16llx sprg3 = %.16llx\n",
426	       vcpu->arch.shregs.sprg2, vcpu->arch.shregs.sprg3);
427	pr_err("cr = %.8lx  xer = %.16lx  dsisr = %.8x\n",
428	       vcpu->arch.regs.ccr, vcpu->arch.regs.xer, vcpu->arch.shregs.dsisr);
429	pr_err("dar = %.16llx\n", vcpu->arch.shregs.dar);
430	pr_err("fault dar = %.16lx dsisr = %.8x\n",
431	       vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
432	pr_err("SLB (%d entries):\n", vcpu->arch.slb_max);
433	for (r = 0; r < vcpu->arch.slb_max; ++r)
434		pr_err("  ESID = %.16llx VSID = %.16llx\n",
435		       vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv);
436	pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n",
437	       vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
438	       vcpu->arch.last_inst);
439}
440
441static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
442{
443	return kvm_get_vcpu_by_id(kvm, id);
444}
445
446static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
447{
448	vpa->__old_status |= LPPACA_OLD_SHARED_PROC;
449	vpa->yield_count = cpu_to_be32(1);
450}
451
452static int set_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *v,
453		   unsigned long addr, unsigned long len)
454{
455	/* check address is cacheline aligned */
456	if (addr & (L1_CACHE_BYTES - 1))
457		return -EINVAL;
458	spin_lock(&vcpu->arch.vpa_update_lock);
459	if (v->next_gpa != addr || v->len != len) {
460		v->next_gpa = addr;
461		v->len = addr ? len : 0;
462		v->update_pending = 1;
463	}
464	spin_unlock(&vcpu->arch.vpa_update_lock);
465	return 0;
466}
467
468/* Length for a per-processor buffer is passed in at offset 4 in the buffer */
469struct reg_vpa {
470	u32 dummy;
471	union {
472		__be16 hword;
473		__be32 word;
474	} length;
475};
476
477static int vpa_is_registered(struct kvmppc_vpa *vpap)
478{
479	if (vpap->update_pending)
480		return vpap->next_gpa != 0;
481	return vpap->pinned_addr != NULL;
482}
483
484static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
485				       unsigned long flags,
486				       unsigned long vcpuid, unsigned long vpa)
487{
488	struct kvm *kvm = vcpu->kvm;
489	unsigned long len, nb;
490	void *va;
491	struct kvm_vcpu *tvcpu;
492	int err;
493	int subfunc;
494	struct kvmppc_vpa *vpap;
495
496	tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
497	if (!tvcpu)
498		return H_PARAMETER;
499
500	subfunc = (flags >> H_VPA_FUNC_SHIFT) & H_VPA_FUNC_MASK;
501	if (subfunc == H_VPA_REG_VPA || subfunc == H_VPA_REG_DTL ||
502	    subfunc == H_VPA_REG_SLB) {
503		/* Registering new area - address must be cache-line aligned */
504		if ((vpa & (L1_CACHE_BYTES - 1)) || !vpa)
505			return H_PARAMETER;
506
507		/* convert logical addr to kernel addr and read length */
508		va = kvmppc_pin_guest_page(kvm, vpa, &nb);
509		if (va == NULL)
510			return H_PARAMETER;
511		if (subfunc == H_VPA_REG_VPA)
512			len = be16_to_cpu(((struct reg_vpa *)va)->length.hword);
513		else
514			len = be32_to_cpu(((struct reg_vpa *)va)->length.word);
515		kvmppc_unpin_guest_page(kvm, va, vpa, false);
516
517		/* Check length */
518		if (len > nb || len < sizeof(struct reg_vpa))
519			return H_PARAMETER;
520	} else {
521		vpa = 0;
522		len = 0;
523	}
524
525	err = H_PARAMETER;
526	vpap = NULL;
527	spin_lock(&tvcpu->arch.vpa_update_lock);
528
529	switch (subfunc) {
530	case H_VPA_REG_VPA:		/* register VPA */
531		/*
532		 * The size of our lppaca is 1kB because of the way we align
533		 * it for the guest to avoid crossing a 4kB boundary. We only
534		 * use 640 bytes of the structure though, so we should accept
535		 * clients that set a size of 640.
536		 */
537		BUILD_BUG_ON(sizeof(struct lppaca) != 640);
538		if (len < sizeof(struct lppaca))
539			break;
540		vpap = &tvcpu->arch.vpa;
541		err = 0;
542		break;
543
544	case H_VPA_REG_DTL:		/* register DTL */
545		if (len < sizeof(struct dtl_entry))
546			break;
547		len -= len % sizeof(struct dtl_entry);
548
549		/* Check that they have previously registered a VPA */
550		err = H_RESOURCE;
551		if (!vpa_is_registered(&tvcpu->arch.vpa))
552			break;
553
554		vpap = &tvcpu->arch.dtl;
555		err = 0;
556		break;
557
558	case H_VPA_REG_SLB:		/* register SLB shadow buffer */
559		/* Check that they have previously registered a VPA */
560		err = H_RESOURCE;
561		if (!vpa_is_registered(&tvcpu->arch.vpa))
562			break;
563
564		vpap = &tvcpu->arch.slb_shadow;
565		err = 0;
566		break;
567
568	case H_VPA_DEREG_VPA:		/* deregister VPA */
569		/* Check they don't still have a DTL or SLB buf registered */
570		err = H_RESOURCE;
571		if (vpa_is_registered(&tvcpu->arch.dtl) ||
572		    vpa_is_registered(&tvcpu->arch.slb_shadow))
573			break;
574
575		vpap = &tvcpu->arch.vpa;
576		err = 0;
577		break;
578
579	case H_VPA_DEREG_DTL:		/* deregister DTL */
580		vpap = &tvcpu->arch.dtl;
581		err = 0;
582		break;
583
584	case H_VPA_DEREG_SLB:		/* deregister SLB shadow buffer */
585		vpap = &tvcpu->arch.slb_shadow;
586		err = 0;
587		break;
588	}
589
590	if (vpap) {
591		vpap->next_gpa = vpa;
592		vpap->len = len;
593		vpap->update_pending = 1;
594	}
595
596	spin_unlock(&tvcpu->arch.vpa_update_lock);
597
598	return err;
599}
600
601static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
602{
603	struct kvm *kvm = vcpu->kvm;
604	void *va;
605	unsigned long nb;
606	unsigned long gpa;
607
608	/*
609	 * We need to pin the page pointed to by vpap->next_gpa,
610	 * but we can't call kvmppc_pin_guest_page under the lock
611	 * as it does get_user_pages() and down_read().  So we
612	 * have to drop the lock, pin the page, then get the lock
613	 * again and check that a new area didn't get registered
614	 * in the meantime.
615	 */
616	for (;;) {
617		gpa = vpap->next_gpa;
618		spin_unlock(&vcpu->arch.vpa_update_lock);
619		va = NULL;
620		nb = 0;
621		if (gpa)
622			va = kvmppc_pin_guest_page(kvm, gpa, &nb);
623		spin_lock(&vcpu->arch.vpa_update_lock);
624		if (gpa == vpap->next_gpa)
625			break;
626		/* sigh... unpin that one and try again */
627		if (va)
628			kvmppc_unpin_guest_page(kvm, va, gpa, false);
629	}
630
631	vpap->update_pending = 0;
632	if (va && nb < vpap->len) {
633		/*
634		 * If it's now too short, it must be that userspace
635		 * has changed the mappings underlying guest memory,
636		 * so unregister the region.
637		 */
638		kvmppc_unpin_guest_page(kvm, va, gpa, false);
639		va = NULL;
640	}
641	if (vpap->pinned_addr)
642		kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
643					vpap->dirty);
644	vpap->gpa = gpa;
645	vpap->pinned_addr = va;
646	vpap->dirty = false;
647	if (va)
648		vpap->pinned_end = va + vpap->len;
649}
650
651static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
652{
653	if (!(vcpu->arch.vpa.update_pending ||
654	      vcpu->arch.slb_shadow.update_pending ||
655	      vcpu->arch.dtl.update_pending))
656		return;
657
658	spin_lock(&vcpu->arch.vpa_update_lock);
659	if (vcpu->arch.vpa.update_pending) {
660		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
661		if (vcpu->arch.vpa.pinned_addr)
662			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
663	}
664	if (vcpu->arch.dtl.update_pending) {
665		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
666		vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
667		vcpu->arch.dtl_index = 0;
668	}
669	if (vcpu->arch.slb_shadow.update_pending)
670		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
671	spin_unlock(&vcpu->arch.vpa_update_lock);
672}
673
674/*
675 * Return the accumulated stolen time for the vcore up until `now'.
676 * The caller should hold the vcore lock.
677 */
678static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
679{
680	u64 p;
681	unsigned long flags;
682
683	spin_lock_irqsave(&vc->stoltb_lock, flags);
684	p = vc->stolen_tb;
685	if (vc->vcore_state != VCORE_INACTIVE &&
686	    vc->preempt_tb != TB_NIL)
687		p += now - vc->preempt_tb;
688	spin_unlock_irqrestore(&vc->stoltb_lock, flags);
689	return p;
690}
691
692static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
693				    struct kvmppc_vcore *vc)
694{
695	struct dtl_entry *dt;
696	struct lppaca *vpa;
697	unsigned long stolen;
698	unsigned long core_stolen;
699	u64 now;
700	unsigned long flags;
701
702	dt = vcpu->arch.dtl_ptr;
703	vpa = vcpu->arch.vpa.pinned_addr;
704	now = mftb();
705	core_stolen = vcore_stolen_time(vc, now);
706	stolen = core_stolen - vcpu->arch.stolen_logged;
707	vcpu->arch.stolen_logged = core_stolen;
708	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
709	stolen += vcpu->arch.busy_stolen;
710	vcpu->arch.busy_stolen = 0;
711	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
712	if (!dt || !vpa)
713		return;
714	memset(dt, 0, sizeof(struct dtl_entry));
715	dt->dispatch_reason = 7;
716	dt->processor_id = cpu_to_be16(vc->pcpu + vcpu->arch.ptid);
717	dt->timebase = cpu_to_be64(now + vc->tb_offset);
718	dt->enqueue_to_dispatch_time = cpu_to_be32(stolen);
719	dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu));
720	dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr);
721	++dt;
722	if (dt == vcpu->arch.dtl.pinned_end)
723		dt = vcpu->arch.dtl.pinned_addr;
724	vcpu->arch.dtl_ptr = dt;
725	/* order writing *dt vs. writing vpa->dtl_idx */
726	smp_wmb();
727	vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index);
728	vcpu->arch.dtl.dirty = true;
729}
730
731/* See if there is a doorbell interrupt pending for a vcpu */
732static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu)
733{
734	int thr;
735	struct kvmppc_vcore *vc;
736
737	if (vcpu->arch.doorbell_request)
738		return true;
739	/*
740	 * Ensure that the read of vcore->dpdes comes after the read
741	 * of vcpu->doorbell_request.  This barrier matches the
742	 * smp_wmb() in kvmppc_guest_entry_inject().
743	 */
744	smp_rmb();
745	vc = vcpu->arch.vcore;
746	thr = vcpu->vcpu_id - vc->first_vcpuid;
747	return !!(vc->dpdes & (1 << thr));
748}
749
750static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu)
751{
752	if (vcpu->arch.vcore->arch_compat >= PVR_ARCH_207)
753		return true;
754	if ((!vcpu->arch.vcore->arch_compat) &&
755	    cpu_has_feature(CPU_FTR_ARCH_207S))
756		return true;
757	return false;
758}
759
760static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
761			     unsigned long resource, unsigned long value1,
762			     unsigned long value2)
763{
764	switch (resource) {
765	case H_SET_MODE_RESOURCE_SET_CIABR:
766		if (!kvmppc_power8_compatible(vcpu))
767			return H_P2;
768		if (value2)
769			return H_P4;
770		if (mflags)
771			return H_UNSUPPORTED_FLAG_START;
772		/* Guests can't breakpoint the hypervisor */
773		if ((value1 & CIABR_PRIV) == CIABR_PRIV_HYPER)
774			return H_P3;
775		vcpu->arch.ciabr  = value1;
776		return H_SUCCESS;
777	case H_SET_MODE_RESOURCE_SET_DAWR0:
778		if (!kvmppc_power8_compatible(vcpu))
779			return H_P2;
780		if (!ppc_breakpoint_available())
781			return H_P2;
782		if (mflags)
783			return H_UNSUPPORTED_FLAG_START;
784		if (value2 & DABRX_HYP)
785			return H_P4;
786		vcpu->arch.dawr  = value1;
787		vcpu->arch.dawrx = value2;
788		return H_SUCCESS;
789	case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE:
790		/* KVM does not support mflags=2 (AIL=2) */
791		if (mflags != 0 && mflags != 3)
792			return H_UNSUPPORTED_FLAG_START;
793		return H_TOO_HARD;
794	default:
795		return H_TOO_HARD;
796	}
797}
798
799/* Copy guest memory in place - must reside within a single memslot */
800static int kvmppc_copy_guest(struct kvm *kvm, gpa_t to, gpa_t from,
801				  unsigned long len)
802{
803	struct kvm_memory_slot *to_memslot = NULL;
804	struct kvm_memory_slot *from_memslot = NULL;
805	unsigned long to_addr, from_addr;
806	int r;
807
808	/* Get HPA for from address */
809	from_memslot = gfn_to_memslot(kvm, from >> PAGE_SHIFT);
810	if (!from_memslot)
811		return -EFAULT;
812	if ((from + len) >= ((from_memslot->base_gfn + from_memslot->npages)
813			     << PAGE_SHIFT))
814		return -EINVAL;
815	from_addr = gfn_to_hva_memslot(from_memslot, from >> PAGE_SHIFT);
816	if (kvm_is_error_hva(from_addr))
817		return -EFAULT;
818	from_addr |= (from & (PAGE_SIZE - 1));
819
820	/* Get HPA for to address */
821	to_memslot = gfn_to_memslot(kvm, to >> PAGE_SHIFT);
822	if (!to_memslot)
823		return -EFAULT;
824	if ((to + len) >= ((to_memslot->base_gfn + to_memslot->npages)
825			   << PAGE_SHIFT))
826		return -EINVAL;
827	to_addr = gfn_to_hva_memslot(to_memslot, to >> PAGE_SHIFT);
828	if (kvm_is_error_hva(to_addr))
829		return -EFAULT;
830	to_addr |= (to & (PAGE_SIZE - 1));
831
832	/* Perform copy */
833	r = raw_copy_in_user((void __user *)to_addr, (void __user *)from_addr,
834			     len);
835	if (r)
836		return -EFAULT;
837	mark_page_dirty(kvm, to >> PAGE_SHIFT);
838	return 0;
839}
840
841static long kvmppc_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
842			       unsigned long dest, unsigned long src)
843{
844	u64 pg_sz = SZ_4K;		/* 4K page size */
845	u64 pg_mask = SZ_4K - 1;
846	int ret;
847
848	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
849	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
850		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
851		return H_PARAMETER;
852
853	/* dest (and src if copy_page flag set) must be page aligned */
854	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
855		return H_PARAMETER;
856
857	/* zero and/or copy the page as determined by the flags */
858	if (flags & H_COPY_PAGE) {
859		ret = kvmppc_copy_guest(vcpu->kvm, dest, src, pg_sz);
860		if (ret < 0)
861			return H_PARAMETER;
862	} else if (flags & H_ZERO_PAGE) {
863		ret = kvm_clear_guest(vcpu->kvm, dest, pg_sz);
864		if (ret < 0)
865			return H_PARAMETER;
866	}
867
868	/* We can ignore the remaining flags */
869
870	return H_SUCCESS;
871}
872
873static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target)
874{
875	struct kvmppc_vcore *vcore = target->arch.vcore;
876
877	/*
878	 * We expect to have been called by the real mode handler
879	 * (kvmppc_rm_h_confer()) which would have directly returned
880	 * H_SUCCESS if the source vcore wasn't idle (e.g. if it may
881	 * have useful work to do and should not confer) so we don't
882	 * recheck that here.
883	 */
884
885	spin_lock(&vcore->lock);
886	if (target->arch.state == KVMPPC_VCPU_RUNNABLE &&
887	    vcore->vcore_state != VCORE_INACTIVE &&
888	    vcore->runner)
889		target = vcore->runner;
890	spin_unlock(&vcore->lock);
891
892	return kvm_vcpu_yield_to(target);
893}
894
895static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
896{
897	int yield_count = 0;
898	struct lppaca *lppaca;
899
900	spin_lock(&vcpu->arch.vpa_update_lock);
901	lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr;
902	if (lppaca)
903		yield_count = be32_to_cpu(lppaca->yield_count);
904	spin_unlock(&vcpu->arch.vpa_update_lock);
905	return yield_count;
906}
907
908int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
909{
910	unsigned long req = kvmppc_get_gpr(vcpu, 3);
911	unsigned long target, ret = H_SUCCESS;
912	int yield_count;
913	struct kvm_vcpu *tvcpu;
914	int idx, rc;
915
916	if (req <= MAX_HCALL_OPCODE &&
917	    !test_bit(req/4, vcpu->kvm->arch.enabled_hcalls))
918		return RESUME_HOST;
919
920	switch (req) {
921	case H_CEDE:
922		break;
923	case H_PROD:
924		target = kvmppc_get_gpr(vcpu, 4);
925		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
926		if (!tvcpu) {
927			ret = H_PARAMETER;
928			break;
929		}
930		tvcpu->arch.prodded = 1;
931		smp_mb();
932		if (tvcpu->arch.ceded)
933			kvmppc_fast_vcpu_kick_hv(tvcpu);
934		break;
935	case H_CONFER:
936		target = kvmppc_get_gpr(vcpu, 4);
937		if (target == -1)
938			break;
939		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
940		if (!tvcpu) {
941			ret = H_PARAMETER;
942			break;
943		}
944		yield_count = kvmppc_get_gpr(vcpu, 5);
945		if (kvmppc_get_yield_count(tvcpu) != yield_count)
946			break;
947		kvm_arch_vcpu_yield_to(tvcpu);
948		break;
949	case H_REGISTER_VPA:
950		ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4),
951					kvmppc_get_gpr(vcpu, 5),
952					kvmppc_get_gpr(vcpu, 6));
953		break;
954	case H_RTAS:
955		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
956			return RESUME_HOST;
957
958		idx = srcu_read_lock(&vcpu->kvm->srcu);
959		rc = kvmppc_rtas_hcall(vcpu);
960		srcu_read_unlock(&vcpu->kvm->srcu, idx);
961
962		if (rc == -ENOENT)
963			return RESUME_HOST;
964		else if (rc == 0)
965			break;
966
967		/* Send the error out to userspace via KVM_RUN */
968		return rc;
969	case H_LOGICAL_CI_LOAD:
970		ret = kvmppc_h_logical_ci_load(vcpu);
971		if (ret == H_TOO_HARD)
972			return RESUME_HOST;
973		break;
974	case H_LOGICAL_CI_STORE:
975		ret = kvmppc_h_logical_ci_store(vcpu);
976		if (ret == H_TOO_HARD)
977			return RESUME_HOST;
978		break;
979	case H_SET_MODE:
980		ret = kvmppc_h_set_mode(vcpu, kvmppc_get_gpr(vcpu, 4),
981					kvmppc_get_gpr(vcpu, 5),
982					kvmppc_get_gpr(vcpu, 6),
983					kvmppc_get_gpr(vcpu, 7));
984		if (ret == H_TOO_HARD)
985			return RESUME_HOST;
986		break;
987	case H_XIRR:
988	case H_CPPR:
989	case H_EOI:
990	case H_IPI:
991	case H_IPOLL:
992	case H_XIRR_X:
993		if (kvmppc_xics_enabled(vcpu)) {
994			if (xics_on_xive()) {
995				ret = H_NOT_AVAILABLE;
996				return RESUME_GUEST;
997			}
998			ret = kvmppc_xics_hcall(vcpu, req);
999			break;
1000		}
1001		return RESUME_HOST;
1002	case H_SET_DABR:
1003		ret = kvmppc_h_set_dabr(vcpu, kvmppc_get_gpr(vcpu, 4));
1004		break;
1005	case H_SET_XDABR:
1006		ret = kvmppc_h_set_xdabr(vcpu, kvmppc_get_gpr(vcpu, 4),
1007						kvmppc_get_gpr(vcpu, 5));
1008		break;
1009#ifdef CONFIG_SPAPR_TCE_IOMMU
1010	case H_GET_TCE:
1011		ret = kvmppc_h_get_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
1012						kvmppc_get_gpr(vcpu, 5));
1013		if (ret == H_TOO_HARD)
1014			return RESUME_HOST;
1015		break;
1016	case H_PUT_TCE:
1017		ret = kvmppc_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
1018						kvmppc_get_gpr(vcpu, 5),
1019						kvmppc_get_gpr(vcpu, 6));
1020		if (ret == H_TOO_HARD)
1021			return RESUME_HOST;
1022		break;
1023	case H_PUT_TCE_INDIRECT:
1024		ret = kvmppc_h_put_tce_indirect(vcpu, kvmppc_get_gpr(vcpu, 4),
1025						kvmppc_get_gpr(vcpu, 5),
1026						kvmppc_get_gpr(vcpu, 6),
1027						kvmppc_get_gpr(vcpu, 7));
1028		if (ret == H_TOO_HARD)
1029			return RESUME_HOST;
1030		break;
1031	case H_STUFF_TCE:
1032		ret = kvmppc_h_stuff_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
1033						kvmppc_get_gpr(vcpu, 5),
1034						kvmppc_get_gpr(vcpu, 6),
1035						kvmppc_get_gpr(vcpu, 7));
1036		if (ret == H_TOO_HARD)
1037			return RESUME_HOST;
1038		break;
1039#endif
1040	case H_RANDOM:
1041		if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4]))
1042			ret = H_HARDWARE;
1043		break;
1044
1045	case H_SET_PARTITION_TABLE:
1046		ret = H_FUNCTION;
1047		if (nesting_enabled(vcpu->kvm))
1048			ret = kvmhv_set_partition_table(vcpu);
1049		break;
1050	case H_ENTER_NESTED:
1051		ret = H_FUNCTION;
1052		if (!nesting_enabled(vcpu->kvm))
1053			break;
1054		ret = kvmhv_enter_nested_guest(vcpu);
1055		if (ret == H_INTERRUPT) {
1056			kvmppc_set_gpr(vcpu, 3, 0);
1057			vcpu->arch.hcall_needed = 0;
1058			return -EINTR;
1059		} else if (ret == H_TOO_HARD) {
1060			kvmppc_set_gpr(vcpu, 3, 0);
1061			vcpu->arch.hcall_needed = 0;
1062			return RESUME_HOST;
1063		}
1064		break;
1065	case H_TLB_INVALIDATE:
1066		ret = H_FUNCTION;
1067		if (nesting_enabled(vcpu->kvm))
1068			ret = kvmhv_do_nested_tlbie(vcpu);
1069		break;
1070	case H_COPY_TOFROM_GUEST:
1071		ret = H_FUNCTION;
1072		if (nesting_enabled(vcpu->kvm))
1073			ret = kvmhv_copy_tofrom_guest_nested(vcpu);
1074		break;
1075	case H_PAGE_INIT:
1076		ret = kvmppc_h_page_init(vcpu, kvmppc_get_gpr(vcpu, 4),
1077					 kvmppc_get_gpr(vcpu, 5),
1078					 kvmppc_get_gpr(vcpu, 6));
1079		break;
1080	case H_SVM_PAGE_IN:
1081		ret = H_UNSUPPORTED;
1082		if (kvmppc_get_srr1(vcpu) & MSR_S)
1083			ret = kvmppc_h_svm_page_in(vcpu->kvm,
1084						   kvmppc_get_gpr(vcpu, 4),
1085						   kvmppc_get_gpr(vcpu, 5),
1086						   kvmppc_get_gpr(vcpu, 6));
1087		break;
1088	case H_SVM_PAGE_OUT:
1089		ret = H_UNSUPPORTED;
1090		if (kvmppc_get_srr1(vcpu) & MSR_S)
1091			ret = kvmppc_h_svm_page_out(vcpu->kvm,
1092						    kvmppc_get_gpr(vcpu, 4),
1093						    kvmppc_get_gpr(vcpu, 5),
1094						    kvmppc_get_gpr(vcpu, 6));
1095		break;
1096	case H_SVM_INIT_START:
1097		ret = H_UNSUPPORTED;
1098		if (kvmppc_get_srr1(vcpu) & MSR_S)
1099			ret = kvmppc_h_svm_init_start(vcpu->kvm);
1100		break;
1101	case H_SVM_INIT_DONE:
1102		ret = H_UNSUPPORTED;
1103		if (kvmppc_get_srr1(vcpu) & MSR_S)
1104			ret = kvmppc_h_svm_init_done(vcpu->kvm);
1105		break;
1106	case H_SVM_INIT_ABORT:
1107		/*
1108		 * Even if that call is made by the Ultravisor, the SSR1 value
1109		 * is the guest context one, with the secure bit clear as it has
1110		 * not yet been secured. So we can't check it here.
1111		 * Instead the kvm->arch.secure_guest flag is checked inside
1112		 * kvmppc_h_svm_init_abort().
1113		 */
1114		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
1115		break;
1116
1117	default:
1118		return RESUME_HOST;
1119	}
1120	kvmppc_set_gpr(vcpu, 3, ret);
1121	vcpu->arch.hcall_needed = 0;
1122	return RESUME_GUEST;
1123}
1124
1125/*
1126 * Handle H_CEDE in the nested virtualization case where we haven't
1127 * called the real-mode hcall handlers in book3s_hv_rmhandlers.S.
1128 * This has to be done early, not in kvmppc_pseries_do_hcall(), so
1129 * that the cede logic in kvmppc_run_single_vcpu() works properly.
1130 */
1131static void kvmppc_nested_cede(struct kvm_vcpu *vcpu)
1132{
1133	vcpu->arch.shregs.msr |= MSR_EE;
1134	vcpu->arch.ceded = 1;
1135	smp_mb();
1136	if (vcpu->arch.prodded) {
1137		vcpu->arch.prodded = 0;
1138		smp_mb();
1139		vcpu->arch.ceded = 0;
1140	}
1141}
1142
1143static int kvmppc_hcall_impl_hv(unsigned long cmd)
1144{
1145	switch (cmd) {
1146	case H_CEDE:
1147	case H_PROD:
1148	case H_CONFER:
1149	case H_REGISTER_VPA:
1150	case H_SET_MODE:
1151	case H_LOGICAL_CI_LOAD:
1152	case H_LOGICAL_CI_STORE:
1153#ifdef CONFIG_KVM_XICS
1154	case H_XIRR:
1155	case H_CPPR:
1156	case H_EOI:
1157	case H_IPI:
1158	case H_IPOLL:
1159	case H_XIRR_X:
1160#endif
1161	case H_PAGE_INIT:
1162		return 1;
1163	}
1164
1165	/* See if it's in the real-mode table */
1166	return kvmppc_hcall_impl_hv_realmode(cmd);
1167}
1168
1169static int kvmppc_emulate_debug_inst(struct kvm_vcpu *vcpu)
1170{
1171	u32 last_inst;
1172
1173	if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) !=
1174					EMULATE_DONE) {
1175		/*
1176		 * Fetch failed, so return to guest and
1177		 * try executing it again.
1178		 */
1179		return RESUME_GUEST;
1180	}
1181
1182	if (last_inst == KVMPPC_INST_SW_BREAKPOINT) {
1183		vcpu->run->exit_reason = KVM_EXIT_DEBUG;
1184		vcpu->run->debug.arch.address = kvmppc_get_pc(vcpu);
1185		return RESUME_HOST;
1186	} else {
1187		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
1188		return RESUME_GUEST;
1189	}
1190}
1191
1192static void do_nothing(void *x)
1193{
1194}
1195
1196static unsigned long kvmppc_read_dpdes(struct kvm_vcpu *vcpu)
1197{
1198	int thr, cpu, pcpu, nthreads;
1199	struct kvm_vcpu *v;
1200	unsigned long dpdes;
1201
1202	nthreads = vcpu->kvm->arch.emul_smt_mode;
1203	dpdes = 0;
1204	cpu = vcpu->vcpu_id & ~(nthreads - 1);
1205	for (thr = 0; thr < nthreads; ++thr, ++cpu) {
1206		v = kvmppc_find_vcpu(vcpu->kvm, cpu);
1207		if (!v)
1208			continue;
1209		/*
1210		 * If the vcpu is currently running on a physical cpu thread,
1211		 * interrupt it in order to pull it out of the guest briefly,
1212		 * which will update its vcore->dpdes value.
1213		 */
1214		pcpu = READ_ONCE(v->cpu);
1215		if (pcpu >= 0)
1216			smp_call_function_single(pcpu, do_nothing, NULL, 1);
1217		if (kvmppc_doorbell_pending(v))
1218			dpdes |= 1 << thr;
1219	}
1220	return dpdes;
1221}
1222
1223/*
1224 * On POWER9, emulate doorbell-related instructions in order to
1225 * give the guest the illusion of running on a multi-threaded core.
1226 * The instructions emulated are msgsndp, msgclrp, mfspr TIR,
1227 * and mfspr DPDES.
1228 */
1229static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu)
1230{
1231	u32 inst, rb, thr;
1232	unsigned long arg;
1233	struct kvm *kvm = vcpu->kvm;
1234	struct kvm_vcpu *tvcpu;
1235
1236	if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst) != EMULATE_DONE)
1237		return RESUME_GUEST;
1238	if (get_op(inst) != 31)
1239		return EMULATE_FAIL;
1240	rb = get_rb(inst);
1241	thr = vcpu->vcpu_id & (kvm->arch.emul_smt_mode - 1);
1242	switch (get_xop(inst)) {
1243	case OP_31_XOP_MSGSNDP:
1244		arg = kvmppc_get_gpr(vcpu, rb);
1245		if (((arg >> 27) & 0xf) != PPC_DBELL_SERVER)
1246			break;
1247		arg &= 0x3f;
1248		if (arg >= kvm->arch.emul_smt_mode)
1249			break;
1250		tvcpu = kvmppc_find_vcpu(kvm, vcpu->vcpu_id - thr + arg);
1251		if (!tvcpu)
1252			break;
1253		if (!tvcpu->arch.doorbell_request) {
1254			tvcpu->arch.doorbell_request = 1;
1255			kvmppc_fast_vcpu_kick_hv(tvcpu);
1256		}
1257		break;
1258	case OP_31_XOP_MSGCLRP:
1259		arg = kvmppc_get_gpr(vcpu, rb);
1260		if (((arg >> 27) & 0xf) != PPC_DBELL_SERVER)
1261			break;
1262		vcpu->arch.vcore->dpdes = 0;
1263		vcpu->arch.doorbell_request = 0;
1264		break;
1265	case OP_31_XOP_MFSPR:
1266		switch (get_sprn(inst)) {
1267		case SPRN_TIR:
1268			arg = thr;
1269			break;
1270		case SPRN_DPDES:
1271			arg = kvmppc_read_dpdes(vcpu);
1272			break;
1273		default:
1274			return EMULATE_FAIL;
1275		}
1276		kvmppc_set_gpr(vcpu, get_rt(inst), arg);
1277		break;
1278	default:
1279		return EMULATE_FAIL;
1280	}
1281	kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4);
1282	return RESUME_GUEST;
1283}
1284
1285static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
1286				 struct task_struct *tsk)
1287{
1288	struct kvm_run *run = vcpu->run;
1289	int r = RESUME_HOST;
1290
1291	vcpu->stat.sum_exits++;
1292
1293	/*
1294	 * This can happen if an interrupt occurs in the last stages
1295	 * of guest entry or the first stages of guest exit (i.e. after
1296	 * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV
1297	 * and before setting it to KVM_GUEST_MODE_HOST_HV).
1298	 * That can happen due to a bug, or due to a machine check
1299	 * occurring at just the wrong time.
1300	 */
1301	if (vcpu->arch.shregs.msr & MSR_HV) {
1302		printk(KERN_EMERG "KVM trap in HV mode!\n");
1303		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
1304			vcpu->arch.trap, kvmppc_get_pc(vcpu),
1305			vcpu->arch.shregs.msr);
1306		kvmppc_dump_regs(vcpu);
1307		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
1308		run->hw.hardware_exit_reason = vcpu->arch.trap;
1309		return RESUME_HOST;
1310	}
1311	run->exit_reason = KVM_EXIT_UNKNOWN;
1312	run->ready_for_interrupt_injection = 1;
1313	switch (vcpu->arch.trap) {
1314	/* We're good on these - the host merely wanted to get our attention */
1315	case BOOK3S_INTERRUPT_HV_DECREMENTER:
1316		vcpu->stat.dec_exits++;
1317		r = RESUME_GUEST;
1318		break;
1319	case BOOK3S_INTERRUPT_EXTERNAL:
1320	case BOOK3S_INTERRUPT_H_DOORBELL:
1321	case BOOK3S_INTERRUPT_H_VIRT:
1322		vcpu->stat.ext_intr_exits++;
1323		r = RESUME_GUEST;
1324		break;
1325	/* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/
1326	case BOOK3S_INTERRUPT_HMI:
1327	case BOOK3S_INTERRUPT_PERFMON:
1328	case BOOK3S_INTERRUPT_SYSTEM_RESET:
1329		r = RESUME_GUEST;
1330		break;
1331	case BOOK3S_INTERRUPT_MACHINE_CHECK:
1332		/* Print the MCE event to host console. */
1333		machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
1334
1335		/*
1336		 * If the guest can do FWNMI, exit to userspace so it can
1337		 * deliver a FWNMI to the guest.
1338		 * Otherwise we synthesize a machine check for the guest
1339		 * so that it knows that the machine check occurred.
1340		 */
1341		if (!vcpu->kvm->arch.fwnmi_enabled) {
1342			ulong flags = vcpu->arch.shregs.msr & 0x083c0000;
1343			kvmppc_core_queue_machine_check(vcpu, flags);
1344			r = RESUME_GUEST;
1345			break;
1346		}
1347
1348		/* Exit to guest with KVM_EXIT_NMI as exit reason */
1349		run->exit_reason = KVM_EXIT_NMI;
1350		run->hw.hardware_exit_reason = vcpu->arch.trap;
1351		/* Clear out the old NMI status from run->flags */
1352		run->flags &= ~KVM_RUN_PPC_NMI_DISP_MASK;
1353		/* Now set the NMI status */
1354		if (vcpu->arch.mce_evt.disposition == MCE_DISPOSITION_RECOVERED)
1355			run->flags |= KVM_RUN_PPC_NMI_DISP_FULLY_RECOV;
1356		else
1357			run->flags |= KVM_RUN_PPC_NMI_DISP_NOT_RECOV;
1358
1359		r = RESUME_HOST;
1360		break;
1361	case BOOK3S_INTERRUPT_PROGRAM:
1362	{
1363		ulong flags;
1364		/*
1365		 * Normally program interrupts are delivered directly
1366		 * to the guest by the hardware, but we can get here
1367		 * as a result of a hypervisor emulation interrupt
1368		 * (e40) getting turned into a 700 by BML RTAS.
1369		 */
1370		flags = vcpu->arch.shregs.msr & 0x1f0000ull;
1371		kvmppc_core_queue_program(vcpu, flags);
1372		r = RESUME_GUEST;
1373		break;
1374	}
1375	case BOOK3S_INTERRUPT_SYSCALL:
1376	{
1377		/* hcall - punt to userspace */
1378		int i;
1379
1380		/* hypercall with MSR_PR has already been handled in rmode,
1381		 * and never reaches here.
1382		 */
1383
1384		run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3);
1385		for (i = 0; i < 9; ++i)
1386			run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i);
1387		run->exit_reason = KVM_EXIT_PAPR_HCALL;
1388		vcpu->arch.hcall_needed = 1;
1389		r = RESUME_HOST;
1390		break;
1391	}
1392	/*
1393	 * We get these next two if the guest accesses a page which it thinks
1394	 * it has mapped but which is not actually present, either because
1395	 * it is for an emulated I/O device or because the corresonding
1396	 * host page has been paged out.  Any other HDSI/HISI interrupts
1397	 * have been handled already.
1398	 */
1399	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
1400		r = RESUME_PAGE_FAULT;
1401		break;
1402	case BOOK3S_INTERRUPT_H_INST_STORAGE:
1403		vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
1404		vcpu->arch.fault_dsisr = vcpu->arch.shregs.msr &
1405			DSISR_SRR1_MATCH_64S;
1406		if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
1407			vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
1408		r = RESUME_PAGE_FAULT;
1409		break;
1410	/*
1411	 * This occurs if the guest executes an illegal instruction.
1412	 * If the guest debug is disabled, generate a program interrupt
1413	 * to the guest. If guest debug is enabled, we need to check
1414	 * whether the instruction is a software breakpoint instruction.
1415	 * Accordingly return to Guest or Host.
1416	 */
1417	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
1418		if (vcpu->arch.emul_inst != KVM_INST_FETCH_FAILED)
1419			vcpu->arch.last_inst = kvmppc_need_byteswap(vcpu) ?
1420				swab32(vcpu->arch.emul_inst) :
1421				vcpu->arch.emul_inst;
1422		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) {
1423			r = kvmppc_emulate_debug_inst(vcpu);
1424		} else {
1425			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
1426			r = RESUME_GUEST;
1427		}
1428		break;
1429	/*
1430	 * This occurs if the guest (kernel or userspace), does something that
1431	 * is prohibited by HFSCR.
1432	 * On POWER9, this could be a doorbell instruction that we need
1433	 * to emulate.
1434	 * Otherwise, we just generate a program interrupt to the guest.
1435	 */
1436	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
1437		r = EMULATE_FAIL;
1438		if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) &&
1439		    cpu_has_feature(CPU_FTR_ARCH_300))
1440			r = kvmppc_emulate_doorbell_instr(vcpu);
1441		if (r == EMULATE_FAIL) {
1442			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
1443			r = RESUME_GUEST;
1444		}
1445		break;
1446
1447#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
1448	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
1449		/*
1450		 * This occurs for various TM-related instructions that
1451		 * we need to emulate on POWER9 DD2.2.  We have already
1452		 * handled the cases where the guest was in real-suspend
1453		 * mode and was transitioning to transactional state.
1454		 */
1455		r = kvmhv_p9_tm_emulation(vcpu);
1456		break;
1457#endif
1458
1459	case BOOK3S_INTERRUPT_HV_RM_HARD:
1460		r = RESUME_PASSTHROUGH;
1461		break;
1462	default:
1463		kvmppc_dump_regs(vcpu);
1464		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
1465			vcpu->arch.trap, kvmppc_get_pc(vcpu),
1466			vcpu->arch.shregs.msr);
1467		run->hw.hardware_exit_reason = vcpu->arch.trap;
1468		r = RESUME_HOST;
1469		break;
1470	}
1471
1472	return r;
1473}
1474
1475static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
1476{
1477	int r;
1478	int srcu_idx;
1479
1480	vcpu->stat.sum_exits++;
1481
1482	/*
1483	 * This can happen if an interrupt occurs in the last stages
1484	 * of guest entry or the first stages of guest exit (i.e. after
1485	 * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV
1486	 * and before setting it to KVM_GUEST_MODE_HOST_HV).
1487	 * That can happen due to a bug, or due to a machine check
1488	 * occurring at just the wrong time.
1489	 */
1490	if (vcpu->arch.shregs.msr & MSR_HV) {
1491		pr_emerg("KVM trap in HV mode while nested!\n");
1492		pr_emerg("trap=0x%x | pc=0x%lx | msr=0x%llx\n",
1493			 vcpu->arch.trap, kvmppc_get_pc(vcpu),
1494			 vcpu->arch.shregs.msr);
1495		kvmppc_dump_regs(vcpu);
1496		return RESUME_HOST;
1497	}
1498	switch (vcpu->arch.trap) {
1499	/* We're good on these - the host merely wanted to get our attention */
1500	case BOOK3S_INTERRUPT_HV_DECREMENTER:
1501		vcpu->stat.dec_exits++;
1502		r = RESUME_GUEST;
1503		break;
1504	case BOOK3S_INTERRUPT_EXTERNAL:
1505		vcpu->stat.ext_intr_exits++;
1506		r = RESUME_HOST;
1507		break;
1508	case BOOK3S_INTERRUPT_H_DOORBELL:
1509	case BOOK3S_INTERRUPT_H_VIRT:
1510		vcpu->stat.ext_intr_exits++;
1511		r = RESUME_GUEST;
1512		break;
1513	/* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/
1514	case BOOK3S_INTERRUPT_HMI:
1515	case BOOK3S_INTERRUPT_PERFMON:
1516	case BOOK3S_INTERRUPT_SYSTEM_RESET:
1517		r = RESUME_GUEST;
1518		break;
1519	case BOOK3S_INTERRUPT_MACHINE_CHECK:
1520		/* Pass the machine check to the L1 guest */
1521		r = RESUME_HOST;
1522		/* Print the MCE event to host console. */
1523		machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
1524		break;
1525	/*
1526	 * We get these next two if the guest accesses a page which it thinks
1527	 * it has mapped but which is not actually present, either because
1528	 * it is for an emulated I/O device or because the corresonding
1529	 * host page has been paged out.
1530	 */
1531	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
1532		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1533		r = kvmhv_nested_page_fault(vcpu);
1534		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
1535		break;
1536	case BOOK3S_INTERRUPT_H_INST_STORAGE:
1537		vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
1538		vcpu->arch.fault_dsisr = kvmppc_get_msr(vcpu) &
1539					 DSISR_SRR1_MATCH_64S;
1540		if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
1541			vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
1542		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1543		r = kvmhv_nested_page_fault(vcpu);
1544		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
1545		break;
1546
1547#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
1548	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
1549		/*
1550		 * This occurs for various TM-related instructions that
1551		 * we need to emulate on POWER9 DD2.2.  We have already
1552		 * handled the cases where the guest was in real-suspend
1553		 * mode and was transitioning to transactional state.
1554		 */
1555		r = kvmhv_p9_tm_emulation(vcpu);
1556		break;
1557#endif
1558
1559	case BOOK3S_INTERRUPT_HV_RM_HARD:
1560		vcpu->arch.trap = 0;
1561		r = RESUME_GUEST;
1562		if (!xics_on_xive())
1563			kvmppc_xics_rm_complete(vcpu, 0);
1564		break;
1565	default:
1566		r = RESUME_HOST;
1567		break;
1568	}
1569
1570	return r;
1571}
1572
1573static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
1574					    struct kvm_sregs *sregs)
1575{
1576	int i;
1577
1578	memset(sregs, 0, sizeof(struct kvm_sregs));
1579	sregs->pvr = vcpu->arch.pvr;
1580	for (i = 0; i < vcpu->arch.slb_max; i++) {
1581		sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige;
1582		sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
1583	}
1584
1585	return 0;
1586}
1587
1588static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
1589					    struct kvm_sregs *sregs)
1590{
1591	int i, j;
1592
1593	/* Only accept the same PVR as the host's, since we can't spoof it */
1594	if (sregs->pvr != vcpu->arch.pvr)
1595		return -EINVAL;
1596
1597	j = 0;
1598	for (i = 0; i < vcpu->arch.slb_nr; i++) {
1599		if (sregs->u.s.ppc64.slb[i].slbe & SLB_ESID_V) {
1600			vcpu->arch.slb[j].orige = sregs->u.s.ppc64.slb[i].slbe;
1601			vcpu->arch.slb[j].origv = sregs->u.s.ppc64.slb[i].slbv;
1602			++j;
1603		}
1604	}
1605	vcpu->arch.slb_max = j;
1606
1607	return 0;
1608}
1609
1610static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
1611		bool preserve_top32)
1612{
1613	struct kvm *kvm = vcpu->kvm;
1614	struct kvmppc_vcore *vc = vcpu->arch.vcore;
1615	u64 mask;
1616
1617	spin_lock(&vc->lock);
1618	/*
1619	 * If ILE (interrupt little-endian) has changed, update the
1620	 * MSR_LE bit in the intr_msr for each vcpu in this vcore.
1621	 */
1622	if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
1623		struct kvm_vcpu *vcpu;
1624		int i;
1625
1626		kvm_for_each_vcpu(i, vcpu, kvm) {
1627			if (vcpu->arch.vcore != vc)
1628				continue;
1629			if (new_lpcr & LPCR_ILE)
1630				vcpu->arch.intr_msr |= MSR_LE;
1631			else
1632				vcpu->arch.intr_msr &= ~MSR_LE;
1633		}
1634	}
1635
1636	/*
1637	 * Userspace can only modify DPFD (default prefetch depth),
1638	 * ILE (interrupt little-endian) and TC (translation control).
1639	 * On POWER8 and POWER9 userspace can also modify AIL (alt. interrupt loc.).
1640	 */
1641	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
1642	if (cpu_has_feature(CPU_FTR_ARCH_207S))
1643		mask |= LPCR_AIL;
1644	/*
1645	 * On POWER9, allow userspace to enable large decrementer for the
1646	 * guest, whether or not the host has it enabled.
1647	 */
1648	if (cpu_has_feature(CPU_FTR_ARCH_300))
1649		mask |= LPCR_LD;
1650
1651	/* Broken 32-bit version of LPCR must not clear top bits */
1652	if (preserve_top32)
1653		mask &= 0xFFFFFFFF;
1654	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
1655	spin_unlock(&vc->lock);
1656}
1657
1658static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
1659				 union kvmppc_one_reg *val)
1660{
1661	int r = 0;
1662	long int i;
1663
1664	switch (id) {
1665	case KVM_REG_PPC_DEBUG_INST:
1666		*val = get_reg_val(id, KVMPPC_INST_SW_BREAKPOINT);
1667		break;
1668	case KVM_REG_PPC_HIOR:
1669		*val = get_reg_val(id, 0);
1670		break;
1671	case KVM_REG_PPC_DABR:
1672		*val = get_reg_val(id, vcpu->arch.dabr);
1673		break;
1674	case KVM_REG_PPC_DABRX:
1675		*val = get_reg_val(id, vcpu->arch.dabrx);
1676		break;
1677	case KVM_REG_PPC_DSCR:
1678		*val = get_reg_val(id, vcpu->arch.dscr);
1679		break;
1680	case KVM_REG_PPC_PURR:
1681		*val = get_reg_val(id, vcpu->arch.purr);
1682		break;
1683	case KVM_REG_PPC_SPURR:
1684		*val = get_reg_val(id, vcpu->arch.spurr);
1685		break;
1686	case KVM_REG_PPC_AMR:
1687		*val = get_reg_val(id, vcpu->arch.amr);
1688		break;
1689	case KVM_REG_PPC_UAMOR:
1690		*val = get_reg_val(id, vcpu->arch.uamor);
1691		break;
1692	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1:
1693		i = id - KVM_REG_PPC_MMCR0;
1694		*val = get_reg_val(id, vcpu->arch.mmcr[i]);
1695		break;
1696	case KVM_REG_PPC_MMCR2:
1697		*val = get_reg_val(id, vcpu->arch.mmcr[2]);
1698		break;
1699	case KVM_REG_PPC_MMCRA:
1700		*val = get_reg_val(id, vcpu->arch.mmcra);
1701		break;
1702	case KVM_REG_PPC_MMCRS:
1703		*val = get_reg_val(id, vcpu->arch.mmcrs);
1704		break;
1705	case KVM_REG_PPC_MMCR3:
1706		*val = get_reg_val(id, vcpu->arch.mmcr[3]);
1707		break;
1708	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
1709		i = id - KVM_REG_PPC_PMC1;
1710		*val = get_reg_val(id, vcpu->arch.pmc[i]);
1711		break;
1712	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
1713		i = id - KVM_REG_PPC_SPMC1;
1714		*val = get_reg_val(id, vcpu->arch.spmc[i]);
1715		break;
1716	case KVM_REG_PPC_SIAR:
1717		*val = get_reg_val(id, vcpu->arch.siar);
1718		break;
1719	case KVM_REG_PPC_SDAR:
1720		*val = get_reg_val(id, vcpu->arch.sdar);
1721		break;
1722	case KVM_REG_PPC_SIER:
1723		*val = get_reg_val(id, vcpu->arch.sier[0]);
1724		break;
1725	case KVM_REG_PPC_SIER2:
1726		*val = get_reg_val(id, vcpu->arch.sier[1]);
1727		break;
1728	case KVM_REG_PPC_SIER3:
1729		*val = get_reg_val(id, vcpu->arch.sier[2]);
1730		break;
1731	case KVM_REG_PPC_IAMR:
1732		*val = get_reg_val(id, vcpu->arch.iamr);
1733		break;
1734	case KVM_REG_PPC_PSPB:
1735		*val = get_reg_val(id, vcpu->arch.pspb);
1736		break;
1737	case KVM_REG_PPC_DPDES:
1738		/*
1739		 * On POWER9, where we are emulating msgsndp etc.,
1740		 * we return 1 bit for each vcpu, which can come from
1741		 * either vcore->dpdes or doorbell_request.
1742		 * On POWER8, doorbell_request is 0.
1743		 */
1744		*val = get_reg_val(id, vcpu->arch.vcore->dpdes |
1745				   vcpu->arch.doorbell_request);
1746		break;
1747	case KVM_REG_PPC_VTB:
1748		*val = get_reg_val(id, vcpu->arch.vcore->vtb);
1749		break;
1750	case KVM_REG_PPC_DAWR:
1751		*val = get_reg_val(id, vcpu->arch.dawr);
1752		break;
1753	case KVM_REG_PPC_DAWRX:
1754		*val = get_reg_val(id, vcpu->arch.dawrx);
1755		break;
1756	case KVM_REG_PPC_CIABR:
1757		*val = get_reg_val(id, vcpu->arch.ciabr);
1758		break;
1759	case KVM_REG_PPC_CSIGR:
1760		*val = get_reg_val(id, vcpu->arch.csigr);
1761		break;
1762	case KVM_REG_PPC_TACR:
1763		*val = get_reg_val(id, vcpu->arch.tacr);
1764		break;
1765	case KVM_REG_PPC_TCSCR:
1766		*val = get_reg_val(id, vcpu->arch.tcscr);
1767		break;
1768	case KVM_REG_PPC_PID:
1769		*val = get_reg_val(id, vcpu->arch.pid);
1770		break;
1771	case KVM_REG_PPC_ACOP:
1772		*val = get_reg_val(id, vcpu->arch.acop);
1773		break;
1774	case KVM_REG_PPC_WORT:
1775		*val = get_reg_val(id, vcpu->arch.wort);
1776		break;
1777	case KVM_REG_PPC_TIDR:
1778		*val = get_reg_val(id, vcpu->arch.tid);
1779		break;
1780	case KVM_REG_PPC_PSSCR:
1781		*val = get_reg_val(id, vcpu->arch.psscr);
1782		break;
1783	case KVM_REG_PPC_VPA_ADDR:
1784		spin_lock(&vcpu->arch.vpa_update_lock);
1785		*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
1786		spin_unlock(&vcpu->arch.vpa_update_lock);
1787		break;
1788	case KVM_REG_PPC_VPA_SLB:
1789		spin_lock(&vcpu->arch.vpa_update_lock);
1790		val->vpaval.addr = vcpu->arch.slb_shadow.next_gpa;
1791		val->vpaval.length = vcpu->arch.slb_shadow.len;
1792		spin_unlock(&vcpu->arch.vpa_update_lock);
1793		break;
1794	case KVM_REG_PPC_VPA_DTL:
1795		spin_lock(&vcpu->arch.vpa_update_lock);
1796		val->vpaval.addr = vcpu->arch.dtl.next_gpa;
1797		val->vpaval.length = vcpu->arch.dtl.len;
1798		spin_unlock(&vcpu->arch.vpa_update_lock);
1799		break;
1800	case KVM_REG_PPC_TB_OFFSET:
1801		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
1802		break;
1803	case KVM_REG_PPC_LPCR:
1804	case KVM_REG_PPC_LPCR_64:
1805		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
1806		break;
1807	case KVM_REG_PPC_PPR:
1808		*val = get_reg_val(id, vcpu->arch.ppr);
1809		break;
1810#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
1811	case KVM_REG_PPC_TFHAR:
1812		*val = get_reg_val(id, vcpu->arch.tfhar);
1813		break;
1814	case KVM_REG_PPC_TFIAR:
1815		*val = get_reg_val(id, vcpu->arch.tfiar);
1816		break;
1817	case KVM_REG_PPC_TEXASR:
1818		*val = get_reg_val(id, vcpu->arch.texasr);
1819		break;
1820	case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
1821		i = id - KVM_REG_PPC_TM_GPR0;
1822		*val = get_reg_val(id, vcpu->arch.gpr_tm[i]);
1823		break;
1824	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
1825	{
1826		int j;
1827		i = id - KVM_REG_PPC_TM_VSR0;
1828		if (i < 32)
1829			for (j = 0; j < TS_FPRWIDTH; j++)
1830				val->vsxval[j] = vcpu->arch.fp_tm.fpr[i][j];
1831		else {
1832			if (cpu_has_feature(CPU_FTR_ALTIVEC))
1833				val->vval = vcpu->arch.vr_tm.vr[i-32];
1834			else
1835				r = -ENXIO;
1836		}
1837		break;
1838	}
1839	case KVM_REG_PPC_TM_CR:
1840		*val = get_reg_val(id, vcpu->arch.cr_tm);
1841		break;
1842	case KVM_REG_PPC_TM_XER:
1843		*val = get_reg_val(id, vcpu->arch.xer_tm);
1844		break;
1845	case KVM_REG_PPC_TM_LR:
1846		*val = get_reg_val(id, vcpu->arch.lr_tm);
1847		break;
1848	case KVM_REG_PPC_TM_CTR:
1849		*val = get_reg_val(id, vcpu->arch.ctr_tm);
1850		break;
1851	case KVM_REG_PPC_TM_FPSCR:
1852		*val = get_reg_val(id, vcpu->arch.fp_tm.fpscr);
1853		break;
1854	case KVM_REG_PPC_TM_AMR:
1855		*val = get_reg_val(id, vcpu->arch.amr_tm);
1856		break;
1857	case KVM_REG_PPC_TM_PPR:
1858		*val = get_reg_val(id, vcpu->arch.ppr_tm);
1859		break;
1860	case KVM_REG_PPC_TM_VRSAVE:
1861		*val = get_reg_val(id, vcpu->arch.vrsave_tm);
1862		break;
1863	case KVM_REG_PPC_TM_VSCR:
1864		if (cpu_has_feature(CPU_FTR_ALTIVEC))
1865			*val = get_reg_val(id, vcpu->arch.vr_tm.vscr.u[3]);
1866		else
1867			r = -ENXIO;
1868		break;
1869	case KVM_REG_PPC_TM_DSCR:
1870		*val = get_reg_val(id, vcpu->arch.dscr_tm);
1871		break;
1872	case KVM_REG_PPC_TM_TAR:
1873		*val = get_reg_val(id, vcpu->arch.tar_tm);
1874		break;
1875#endif
1876	case KVM_REG_PPC_ARCH_COMPAT:
1877		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
1878		break;
1879	case KVM_REG_PPC_DEC_EXPIRY:
1880		*val = get_reg_val(id, vcpu->arch.dec_expires +
1881				   vcpu->arch.vcore->tb_offset);
1882		break;
1883	case KVM_REG_PPC_ONLINE:
1884		*val = get_reg_val(id, vcpu->arch.online);
1885		break;
1886	case KVM_REG_PPC_PTCR:
1887		*val = get_reg_val(id, vcpu->kvm->arch.l1_ptcr);
1888		break;
1889	default:
1890		r = -EINVAL;
1891		break;
1892	}
1893
1894	return r;
1895}
1896
1897static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
1898				 union kvmppc_one_reg *val)
1899{
1900	int r = 0;
1901	long int i;
1902	unsigned long addr, len;
1903
1904	switch (id) {
1905	case KVM_REG_PPC_HIOR:
1906		/* Only allow this to be set to zero */
1907		if (set_reg_val(id, *val))
1908			r = -EINVAL;
1909		break;
1910	case KVM_REG_PPC_DABR:
1911		vcpu->arch.dabr = set_reg_val(id, *val);
1912		break;
1913	case KVM_REG_PPC_DABRX:
1914		vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP;
1915		break;
1916	case KVM_REG_PPC_DSCR:
1917		vcpu->arch.dscr = set_reg_val(id, *val);
1918		break;
1919	case KVM_REG_PPC_PURR:
1920		vcpu->arch.purr = set_reg_val(id, *val);
1921		break;
1922	case KVM_REG_PPC_SPURR:
1923		vcpu->arch.spurr = set_reg_val(id, *val);
1924		break;
1925	case KVM_REG_PPC_AMR:
1926		vcpu->arch.amr = set_reg_val(id, *val);
1927		break;
1928	case KVM_REG_PPC_UAMOR:
1929		vcpu->arch.uamor = set_reg_val(id, *val);
1930		break;
1931	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1:
1932		i = id - KVM_REG_PPC_MMCR0;
1933		vcpu->arch.mmcr[i] = set_reg_val(id, *val);
1934		break;
1935	case KVM_REG_PPC_MMCR2:
1936		vcpu->arch.mmcr[2] = set_reg_val(id, *val);
1937		break;
1938	case KVM_REG_PPC_MMCRA:
1939		vcpu->arch.mmcra = set_reg_val(id, *val);
1940		break;
1941	case KVM_REG_PPC_MMCRS:
1942		vcpu->arch.mmcrs = set_reg_val(id, *val);
1943		break;
1944	case KVM_REG_PPC_MMCR3:
1945		*val = get_reg_val(id, vcpu->arch.mmcr[3]);
1946		break;
1947	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
1948		i = id - KVM_REG_PPC_PMC1;
1949		vcpu->arch.pmc[i] = set_reg_val(id, *val);
1950		break;
1951	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
1952		i = id - KVM_REG_PPC_SPMC1;
1953		vcpu->arch.spmc[i] = set_reg_val(id, *val);
1954		break;
1955	case KVM_REG_PPC_SIAR:
1956		vcpu->arch.siar = set_reg_val(id, *val);
1957		break;
1958	case KVM_REG_PPC_SDAR:
1959		vcpu->arch.sdar = set_reg_val(id, *val);
1960		break;
1961	case KVM_REG_PPC_SIER:
1962		vcpu->arch.sier[0] = set_reg_val(id, *val);
1963		break;
1964	case KVM_REG_PPC_SIER2:
1965		vcpu->arch.sier[1] = set_reg_val(id, *val);
1966		break;
1967	case KVM_REG_PPC_SIER3:
1968		vcpu->arch.sier[2] = set_reg_val(id, *val);
1969		break;
1970	case KVM_REG_PPC_IAMR:
1971		vcpu->arch.iamr = set_reg_val(id, *val);
1972		break;
1973	case KVM_REG_PPC_PSPB:
1974		vcpu->arch.pspb = set_reg_val(id, *val);
1975		break;
1976	case KVM_REG_PPC_DPDES:
1977		vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
1978		break;
1979	case KVM_REG_PPC_VTB:
1980		vcpu->arch.vcore->vtb = set_reg_val(id, *val);
1981		break;
1982	case KVM_REG_PPC_DAWR:
1983		vcpu->arch.dawr = set_reg_val(id, *val);
1984		break;
1985	case KVM_REG_PPC_DAWRX:
1986		vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
1987		break;
1988	case KVM_REG_PPC_CIABR:
1989		vcpu->arch.ciabr = set_reg_val(id, *val);
1990		/* Don't allow setting breakpoints in hypervisor code */
1991		if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
1992			vcpu->arch.ciabr &= ~CIABR_PRIV;	/* disable */
1993		break;
1994	case KVM_REG_PPC_CSIGR:
1995		vcpu->arch.csigr = set_reg_val(id, *val);
1996		break;
1997	case KVM_REG_PPC_TACR:
1998		vcpu->arch.tacr = set_reg_val(id, *val);
1999		break;
2000	case KVM_REG_PPC_TCSCR:
2001		vcpu->arch.tcscr = set_reg_val(id, *val);
2002		break;
2003	case KVM_REG_PPC_PID:
2004		vcpu->arch.pid = set_reg_val(id, *val);
2005		break;
2006	case KVM_REG_PPC_ACOP:
2007		vcpu->arch.acop = set_reg_val(id, *val);
2008		break;
2009	case KVM_REG_PPC_WORT:
2010		vcpu->arch.wort = set_reg_val(id, *val);
2011		break;
2012	case KVM_REG_PPC_TIDR:
2013		vcpu->arch.tid = set_reg_val(id, *val);
2014		break;
2015	case KVM_REG_PPC_PSSCR:
2016		vcpu->arch.psscr = set_reg_val(id, *val) & PSSCR_GUEST_VIS;
2017		break;
2018	case KVM_REG_PPC_VPA_ADDR:
2019		addr = set_reg_val(id, *val);
2020		r = -EINVAL;
2021		if (!addr && (vcpu->arch.slb_shadow.next_gpa ||
2022			      vcpu->arch.dtl.next_gpa))
2023			break;
2024		r = set_vpa(vcpu, &vcpu->arch.vpa, addr, sizeof(struct lppaca));
2025		break;
2026	case KVM_REG_PPC_VPA_SLB:
2027		addr = val->vpaval.addr;
2028		len = val->vpaval.length;
2029		r = -EINVAL;
2030		if (addr && !vcpu->arch.vpa.next_gpa)
2031			break;
2032		r = set_vpa(vcpu, &vcpu->arch.slb_shadow, addr, len);
2033		break;
2034	case KVM_REG_PPC_VPA_DTL:
2035		addr = val->vpaval.addr;
2036		len = val->vpaval.length;
2037		r = -EINVAL;
2038		if (addr && (len < sizeof(struct dtl_entry) ||
2039			     !vcpu->arch.vpa.next_gpa))
2040			break;
2041		len -= len % sizeof(struct dtl_entry);
2042		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
2043		break;
2044	case KVM_REG_PPC_TB_OFFSET:
2045		/* round up to multiple of 2^24 */
2046		vcpu->arch.vcore->tb_offset =
2047			ALIGN(set_reg_val(id, *val), 1UL << 24);
2048		break;
2049	case KVM_REG_PPC_LPCR:
2050		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), true);
2051		break;
2052	case KVM_REG_PPC_LPCR_64:
2053		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), false);
2054		break;
2055	case KVM_REG_PPC_PPR:
2056		vcpu->arch.ppr = set_reg_val(id, *val);
2057		break;
2058#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2059	case KVM_REG_PPC_TFHAR:
2060		vcpu->arch.tfhar = set_reg_val(id, *val);
2061		break;
2062	case KVM_REG_PPC_TFIAR:
2063		vcpu->arch.tfiar = set_reg_val(id, *val);
2064		break;
2065	case KVM_REG_PPC_TEXASR:
2066		vcpu->arch.texasr = set_reg_val(id, *val);
2067		break;
2068	case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
2069		i = id - KVM_REG_PPC_TM_GPR0;
2070		vcpu->arch.gpr_tm[i] = set_reg_val(id, *val);
2071		break;
2072	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
2073	{
2074		int j;
2075		i = id - KVM_REG_PPC_TM_VSR0;
2076		if (i < 32)
2077			for (j = 0; j < TS_FPRWIDTH; j++)
2078				vcpu->arch.fp_tm.fpr[i][j] = val->vsxval[j];
2079		else
2080			if (cpu_has_feature(CPU_FTR_ALTIVEC))
2081				vcpu->arch.vr_tm.vr[i-32] = val->vval;
2082			else
2083				r = -ENXIO;
2084		break;
2085	}
2086	case KVM_REG_PPC_TM_CR:
2087		vcpu->arch.cr_tm = set_reg_val(id, *val);
2088		break;
2089	case KVM_REG_PPC_TM_XER:
2090		vcpu->arch.xer_tm = set_reg_val(id, *val);
2091		break;
2092	case KVM_REG_PPC_TM_LR:
2093		vcpu->arch.lr_tm = set_reg_val(id, *val);
2094		break;
2095	case KVM_REG_PPC_TM_CTR:
2096		vcpu->arch.ctr_tm = set_reg_val(id, *val);
2097		break;
2098	case KVM_REG_PPC_TM_FPSCR:
2099		vcpu->arch.fp_tm.fpscr = set_reg_val(id, *val);
2100		break;
2101	case KVM_REG_PPC_TM_AMR:
2102		vcpu->arch.amr_tm = set_reg_val(id, *val);
2103		break;
2104	case KVM_REG_PPC_TM_PPR:
2105		vcpu->arch.ppr_tm = set_reg_val(id, *val);
2106		break;
2107	case KVM_REG_PPC_TM_VRSAVE:
2108		vcpu->arch.vrsave_tm = set_reg_val(id, *val);
2109		break;
2110	case KVM_REG_PPC_TM_VSCR:
2111		if (cpu_has_feature(CPU_FTR_ALTIVEC))
2112			vcpu->arch.vr.vscr.u[3] = set_reg_val(id, *val);
2113		else
2114			r = - ENXIO;
2115		break;
2116	case KVM_REG_PPC_TM_DSCR:
2117		vcpu->arch.dscr_tm = set_reg_val(id, *val);
2118		break;
2119	case KVM_REG_PPC_TM_TAR:
2120		vcpu->arch.tar_tm = set_reg_val(id, *val);
2121		break;
2122#endif
2123	case KVM_REG_PPC_ARCH_COMPAT:
2124		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
2125		break;
2126	case KVM_REG_PPC_DEC_EXPIRY:
2127		vcpu->arch.dec_expires = set_reg_val(id, *val) -
2128			vcpu->arch.vcore->tb_offset;
2129		break;
2130	case KVM_REG_PPC_ONLINE:
2131		i = set_reg_val(id, *val);
2132		if (i && !vcpu->arch.online)
2133			atomic_inc(&vcpu->arch.vcore->online_count);
2134		else if (!i && vcpu->arch.online)
2135			atomic_dec(&vcpu->arch.vcore->online_count);
2136		vcpu->arch.online = i;
2137		break;
2138	case KVM_REG_PPC_PTCR:
2139		vcpu->kvm->arch.l1_ptcr = set_reg_val(id, *val);
2140		break;
2141	default:
2142		r = -EINVAL;
2143		break;
2144	}
2145
2146	return r;
2147}
2148
2149/*
2150 * On POWER9, threads are independent and can be in different partitions.
2151 * Therefore we consider each thread to be a subcore.
2152 * There is a restriction that all threads have to be in the same
2153 * MMU mode (radix or HPT), unfortunately, but since we only support
2154 * HPT guests on a HPT host so far, that isn't an impediment yet.
2155 */
2156static int threads_per_vcore(struct kvm *kvm)
2157{
2158	if (kvm->arch.threads_indep)
2159		return 1;
2160	return threads_per_subcore;
2161}
2162
2163static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id)
2164{
2165	struct kvmppc_vcore *vcore;
2166
2167	vcore = kzalloc(sizeof(struct kvmppc_vcore), GFP_KERNEL);
2168
2169	if (vcore == NULL)
2170		return NULL;
2171
2172	spin_lock_init(&vcore->lock);
2173	spin_lock_init(&vcore->stoltb_lock);
2174	rcuwait_init(&vcore->wait);
2175	vcore->preempt_tb = TB_NIL;
2176	vcore->lpcr = kvm->arch.lpcr;
2177	vcore->first_vcpuid = id;
2178	vcore->kvm = kvm;
2179	INIT_LIST_HEAD(&vcore->preempt_list);
2180
2181	return vcore;
2182}
2183
2184#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
2185static struct debugfs_timings_element {
2186	const char *name;
2187	size_t offset;
2188} timings[] = {
2189	{"rm_entry",	offsetof(struct kvm_vcpu, arch.rm_entry)},
2190	{"rm_intr",	offsetof(struct kvm_vcpu, arch.rm_intr)},
2191	{"rm_exit",	offsetof(struct kvm_vcpu, arch.rm_exit)},
2192	{"guest",	offsetof(struct kvm_vcpu, arch.guest_time)},
2193	{"cede",	offsetof(struct kvm_vcpu, arch.cede_time)},
2194};
2195
2196#define N_TIMINGS	(ARRAY_SIZE(timings))
2197
2198struct debugfs_timings_state {
2199	struct kvm_vcpu	*vcpu;
2200	unsigned int	buflen;
2201	char		buf[N_TIMINGS * 100];
2202};
2203
2204static int debugfs_timings_open(struct inode *inode, struct file *file)
2205{
2206	struct kvm_vcpu *vcpu = inode->i_private;
2207	struct debugfs_timings_state *p;
2208
2209	p = kzalloc(sizeof(*p), GFP_KERNEL);
2210	if (!p)
2211		return -ENOMEM;
2212
2213	kvm_get_kvm(vcpu->kvm);
2214	p->vcpu = vcpu;
2215	file->private_data = p;
2216
2217	return nonseekable_open(inode, file);
2218}
2219
2220static int debugfs_timings_release(struct inode *inode, struct file *file)
2221{
2222	struct debugfs_timings_state *p = file->private_data;
2223
2224	kvm_put_kvm(p->vcpu->kvm);
2225	kfree(p);
2226	return 0;
2227}
2228
2229static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
2230				    size_t len, loff_t *ppos)
2231{
2232	struct debugfs_timings_state *p = file->private_data;
2233	struct kvm_vcpu *vcpu = p->vcpu;
2234	char *s, *buf_end;
2235	struct kvmhv_tb_accumulator tb;
2236	u64 count;
2237	loff_t pos;
2238	ssize_t n;
2239	int i, loops;
2240	bool ok;
2241
2242	if (!p->buflen) {
2243		s = p->buf;
2244		buf_end = s + sizeof(p->buf);
2245		for (i = 0; i < N_TIMINGS; ++i) {
2246			struct kvmhv_tb_accumulator *acc;
2247
2248			acc = (struct kvmhv_tb_accumulator *)
2249				((unsigned long)vcpu + timings[i].offset);
2250			ok = false;
2251			for (loops = 0; loops < 1000; ++loops) {
2252				count = acc->seqcount;
2253				if (!(count & 1)) {
2254					smp_rmb();
2255					tb = *acc;
2256					smp_rmb();
2257					if (count == acc->seqcount) {
2258						ok = true;
2259						break;
2260					}
2261				}
2262				udelay(1);
2263			}
2264			if (!ok)
2265				snprintf(s, buf_end - s, "%s: stuck\n",
2266					timings[i].name);
2267			else
2268				snprintf(s, buf_end - s,
2269					"%s: %llu %llu %llu %llu\n",
2270					timings[i].name, count / 2,
2271					tb_to_ns(tb.tb_total),
2272					tb_to_ns(tb.tb_min),
2273					tb_to_ns(tb.tb_max));
2274			s += strlen(s);
2275		}
2276		p->buflen = s - p->buf;
2277	}
2278
2279	pos = *ppos;
2280	if (pos >= p->buflen)
2281		return 0;
2282	if (len > p->buflen - pos)
2283		len = p->buflen - pos;
2284	n = copy_to_user(buf, p->buf + pos, len);
2285	if (n) {
2286		if (n == len)
2287			return -EFAULT;
2288		len -= n;
2289	}
2290	*ppos = pos + len;
2291	return len;
2292}
2293
2294static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
2295				     size_t len, loff_t *ppos)
2296{
2297	return -EACCES;
2298}
2299
2300static const struct file_operations debugfs_timings_ops = {
2301	.owner	 = THIS_MODULE,
2302	.open	 = debugfs_timings_open,
2303	.release = debugfs_timings_release,
2304	.read	 = debugfs_timings_read,
2305	.write	 = debugfs_timings_write,
2306	.llseek	 = generic_file_llseek,
2307};
2308
2309/* Create a debugfs directory for the vcpu */
2310static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
2311{
2312	char buf[16];
2313	struct kvm *kvm = vcpu->kvm;
2314
2315	snprintf(buf, sizeof(buf), "vcpu%u", id);
2316	vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
2317	debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir, vcpu,
2318			    &debugfs_timings_ops);
2319}
2320
2321#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
2322static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
2323{
2324}
2325#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
2326
2327static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
2328{
2329	int err;
2330	int core;
2331	struct kvmppc_vcore *vcore;
2332	struct kvm *kvm;
2333	unsigned int id;
2334
2335	kvm = vcpu->kvm;
2336	id = vcpu->vcpu_id;
2337
2338	vcpu->arch.shared = &vcpu->arch.shregs;
2339#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
2340	/*
2341	 * The shared struct is never shared on HV,
2342	 * so we can always use host endianness
2343	 */
2344#ifdef __BIG_ENDIAN__
2345	vcpu->arch.shared_big_endian = true;
2346#else
2347	vcpu->arch.shared_big_endian = false;
2348#endif
2349#endif
2350	vcpu->arch.mmcr[0] = MMCR0_FC;
2351	vcpu->arch.ctrl = CTRL_RUNLATCH;
2352	/* default to host PVR, since we can't spoof it */
2353	kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
2354	spin_lock_init(&vcpu->arch.vpa_update_lock);
2355	spin_lock_init(&vcpu->arch.tbacct_lock);
2356	vcpu->arch.busy_preempt = TB_NIL;
2357	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
2358
2359	/*
2360	 * Set the default HFSCR for the guest from the host value.
2361	 * This value is only used on POWER9.
2362	 * On POWER9, we want to virtualize the doorbell facility, so we
2363	 * don't set the HFSCR_MSGP bit, and that causes those instructions
2364	 * to trap and then we emulate them.
2365	 */
2366	vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB |
2367		HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX;
2368	if (cpu_has_feature(CPU_FTR_HVMODE)) {
2369		vcpu->arch.hfscr &= mfspr(SPRN_HFSCR);
2370#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2371		if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
2372			vcpu->arch.hfscr |= HFSCR_TM;
2373#endif
2374	}
2375	if (cpu_has_feature(CPU_FTR_TM_COMP))
2376		vcpu->arch.hfscr |= HFSCR_TM;
2377
2378	kvmppc_mmu_book3s_hv_init(vcpu);
2379
2380	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
2381
2382	init_waitqueue_head(&vcpu->arch.cpu_run);
2383
2384	mutex_lock(&kvm->lock);
2385	vcore = NULL;
2386	err = -EINVAL;
2387	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
2388		if (id >= (KVM_MAX_VCPUS * kvm->arch.emul_smt_mode)) {
2389			pr_devel("KVM: VCPU ID too high\n");
2390			core = KVM_MAX_VCORES;
2391		} else {
2392			BUG_ON(kvm->arch.smt_mode != 1);
2393			core = kvmppc_pack_vcpu_id(kvm, id);
2394		}
2395	} else {
2396		core = id / kvm->arch.smt_mode;
2397	}
2398	if (core < KVM_MAX_VCORES) {
2399		vcore = kvm->arch.vcores[core];
2400		if (vcore && cpu_has_feature(CPU_FTR_ARCH_300)) {
2401			pr_devel("KVM: collision on id %u", id);
2402			vcore = NULL;
2403		} else if (!vcore) {
2404			/*
2405			 * Take mmu_setup_lock for mutual exclusion
2406			 * with kvmppc_update_lpcr().
2407			 */
2408			err = -ENOMEM;
2409			vcore = kvmppc_vcore_create(kvm,
2410					id & ~(kvm->arch.smt_mode - 1));
2411			mutex_lock(&kvm->arch.mmu_setup_lock);
2412			kvm->arch.vcores[core] = vcore;
2413			kvm->arch.online_vcores++;
2414			mutex_unlock(&kvm->arch.mmu_setup_lock);
2415		}
2416	}
2417	mutex_unlock(&kvm->lock);
2418
2419	if (!vcore)
2420		return err;
2421
2422	spin_lock(&vcore->lock);
2423	++vcore->num_threads;
2424	spin_unlock(&vcore->lock);
2425	vcpu->arch.vcore = vcore;
2426	vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid;
2427	vcpu->arch.thread_cpu = -1;
2428	vcpu->arch.prev_cpu = -1;
2429
2430	vcpu->arch.cpu_type = KVM_CPU_3S_64;
2431	kvmppc_sanity_check(vcpu);
2432
2433	debugfs_vcpu_init(vcpu, id);
2434
2435	return 0;
2436}
2437
2438static int kvmhv_set_smt_mode(struct kvm *kvm, unsigned long smt_mode,
2439			      unsigned long flags)
2440{
2441	int err;
2442	int esmt = 0;
2443
2444	if (flags)
2445		return -EINVAL;
2446	if (smt_mode > MAX_SMT_THREADS || !is_power_of_2(smt_mode))
2447		return -EINVAL;
2448	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
2449		/*
2450		 * On POWER8 (or POWER7), the threading mode is "strict",
2451		 * so we pack smt_mode vcpus per vcore.
2452		 */
2453		if (smt_mode > threads_per_subcore)
2454			return -EINVAL;
2455	} else {
2456		/*
2457		 * On POWER9, the threading mode is "loose",
2458		 * so each vcpu gets its own vcore.
2459		 */
2460		esmt = smt_mode;
2461		smt_mode = 1;
2462	}
2463	mutex_lock(&kvm->lock);
2464	err = -EBUSY;
2465	if (!kvm->arch.online_vcores) {
2466		kvm->arch.smt_mode = smt_mode;
2467		kvm->arch.emul_smt_mode = esmt;
2468		err = 0;
2469	}
2470	mutex_unlock(&kvm->lock);
2471
2472	return err;
2473}
2474
2475static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa)
2476{
2477	if (vpa->pinned_addr)
2478		kvmppc_unpin_guest_page(kvm, vpa->pinned_addr, vpa->gpa,
2479					vpa->dirty);
2480}
2481
2482static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
2483{
2484	spin_lock(&vcpu->arch.vpa_update_lock);
2485	unpin_vpa(vcpu->kvm, &vcpu->arch.dtl);
2486	unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
2487	unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
2488	spin_unlock(&vcpu->arch.vpa_update_lock);
2489}
2490
2491static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
2492{
2493	/* Indicate we want to get back into the guest */
2494	return 1;
2495}
2496
2497static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
2498{
2499	unsigned long dec_nsec, now;
2500
2501	now = get_tb();
2502	if (now > vcpu->arch.dec_expires) {
2503		/* decrementer has already gone negative */
2504		kvmppc_core_queue_dec(vcpu);
2505		kvmppc_core_prepare_to_enter(vcpu);
2506		return;
2507	}
2508	dec_nsec = tb_to_ns(vcpu->arch.dec_expires - now);
2509	hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL);
2510	vcpu->arch.timer_running = 1;
2511}
2512
2513extern int __kvmppc_vcore_entry(void);
2514
2515static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
2516				   struct kvm_vcpu *vcpu)
2517{
2518	u64 now;
2519
2520	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
2521		return;
2522	spin_lock_irq(&vcpu->arch.tbacct_lock);
2523	now = mftb();
2524	vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
2525		vcpu->arch.stolen_logged;
2526	vcpu->arch.busy_preempt = now;
2527	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
2528	spin_unlock_irq(&vcpu->arch.tbacct_lock);
2529	--vc->n_runnable;
2530	WRITE_ONCE(vc->runnable_threads[vcpu->arch.ptid], NULL);
2531}
2532
2533static int kvmppc_grab_hwthread(int cpu)
2534{
2535	struct paca_struct *tpaca;
2536	long timeout = 10000;
2537
2538	tpaca = paca_ptrs[cpu];
2539
2540	/* Ensure the thread won't go into the kernel if it wakes */
2541	tpaca->kvm_hstate.kvm_vcpu = NULL;
2542	tpaca->kvm_hstate.kvm_vcore = NULL;
2543	tpaca->kvm_hstate.napping = 0;
2544	smp_wmb();
2545	tpaca->kvm_hstate.hwthread_req = 1;
2546
2547	/*
2548	 * If the thread is already executing in the kernel (e.g. handling
2549	 * a stray interrupt), wait for it to get back to nap mode.
2550	 * The smp_mb() is to ensure that our setting of hwthread_req
2551	 * is visible before we look at hwthread_state, so if this
2552	 * races with the code at system_reset_pSeries and the thread
2553	 * misses our setting of hwthread_req, we are sure to see its
2554	 * setting of hwthread_state, and vice versa.
2555	 */
2556	smp_mb();
2557	while (tpaca->kvm_hstate.hwthread_state == KVM_HWTHREAD_IN_KERNEL) {
2558		if (--timeout <= 0) {
2559			pr_err("KVM: couldn't grab cpu %d\n", cpu);
2560			return -EBUSY;
2561		}
2562		udelay(1);
2563	}
2564	return 0;
2565}
2566
2567static void kvmppc_release_hwthread(int cpu)
2568{
2569	struct paca_struct *tpaca;
2570
2571	tpaca = paca_ptrs[cpu];
2572	tpaca->kvm_hstate.hwthread_req = 0;
2573	tpaca->kvm_hstate.kvm_vcpu = NULL;
2574	tpaca->kvm_hstate.kvm_vcore = NULL;
2575	tpaca->kvm_hstate.kvm_split_mode = NULL;
2576}
2577
2578static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
2579{
2580	struct kvm_nested_guest *nested = vcpu->arch.nested;
2581	cpumask_t *cpu_in_guest;
2582	int i;
2583
2584	cpu = cpu_first_tlb_thread_sibling(cpu);
2585	if (nested) {
2586		cpumask_set_cpu(cpu, &nested->need_tlb_flush);
2587		cpu_in_guest = &nested->cpu_in_guest;
2588	} else {
2589		cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush);
2590		cpu_in_guest = &kvm->arch.cpu_in_guest;
2591	}
2592	/*
2593	 * Make sure setting of bit in need_tlb_flush precedes
2594	 * testing of cpu_in_guest bits.  The matching barrier on
2595	 * the other side is the first smp_mb() in kvmppc_run_core().
2596	 */
2597	smp_mb();
2598	for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu);
2599					i += cpu_tlb_thread_sibling_step())
2600		if (cpumask_test_cpu(i, cpu_in_guest))
2601			smp_call_function_single(i, do_nothing, NULL, 1);
2602}
2603
2604static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
2605{
2606	struct kvm_nested_guest *nested = vcpu->arch.nested;
2607	struct kvm *kvm = vcpu->kvm;
2608	int prev_cpu;
2609
2610	if (!cpu_has_feature(CPU_FTR_HVMODE))
2611		return;
2612
2613	if (nested)
2614		prev_cpu = nested->prev_cpu[vcpu->arch.nested_vcpu_id];
2615	else
2616		prev_cpu = vcpu->arch.prev_cpu;
2617
2618	/*
2619	 * With radix, the guest can do TLB invalidations itself,
2620	 * and it could choose to use the local form (tlbiel) if
2621	 * it is invalidating a translation that has only ever been
2622	 * used on one vcpu.  However, that doesn't mean it has
2623	 * only ever been used on one physical cpu, since vcpus
2624	 * can move around between pcpus.  To cope with this, when
2625	 * a vcpu moves from one pcpu to another, we need to tell
2626	 * any vcpus running on the same core as this vcpu previously
2627	 * ran to flush the TLB.  The TLB is shared between threads,
2628	 * so we use a single bit in .need_tlb_flush for all 4 threads.
2629	 */
2630	if (prev_cpu != pcpu) {
2631		if (prev_cpu >= 0 &&
2632		    cpu_first_tlb_thread_sibling(prev_cpu) !=
2633		    cpu_first_tlb_thread_sibling(pcpu))
2634			radix_flush_cpu(kvm, prev_cpu, vcpu);
2635		if (nested)
2636			nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu;
2637		else
2638			vcpu->arch.prev_cpu = pcpu;
2639	}
2640}
2641
2642static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
2643{
2644	int cpu;
2645	struct paca_struct *tpaca;
2646	struct kvm *kvm = vc->kvm;
2647
2648	cpu = vc->pcpu;
2649	if (vcpu) {
2650		if (vcpu->arch.timer_running) {
2651			hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
2652			vcpu->arch.timer_running = 0;
2653		}
2654		cpu += vcpu->arch.ptid;
2655		vcpu->cpu = vc->pcpu;
2656		vcpu->arch.thread_cpu = cpu;
2657		cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest);
2658	}
2659	tpaca = paca_ptrs[cpu];
2660	tpaca->kvm_hstate.kvm_vcpu = vcpu;
2661	tpaca->kvm_hstate.ptid = cpu - vc->pcpu;
2662	tpaca->kvm_hstate.fake_suspend = 0;
2663	/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
2664	smp_wmb();
2665	tpaca->kvm_hstate.kvm_vcore = vc;
2666	if (cpu != smp_processor_id())
2667		kvmppc_ipi_thread(cpu);
2668}
2669
2670static void kvmppc_wait_for_nap(int n_threads)
2671{
2672	int cpu = smp_processor_id();
2673	int i, loops;
2674
2675	if (n_threads <= 1)
2676		return;
2677	for (loops = 0; loops < 1000000; ++loops) {
2678		/*
2679		 * Check if all threads are finished.
2680		 * We set the vcore pointer when starting a thread
2681		 * and the thread clears it when finished, so we look
2682		 * for any threads that still have a non-NULL vcore ptr.
2683		 */
2684		for (i = 1; i < n_threads; ++i)
2685			if (paca_ptrs[cpu + i]->kvm_hstate.kvm_vcore)
2686				break;
2687		if (i == n_threads) {
2688			HMT_medium();
2689			return;
2690		}
2691		HMT_low();
2692	}
2693	HMT_medium();
2694	for (i = 1; i < n_threads; ++i)
2695		if (paca_ptrs[cpu + i]->kvm_hstate.kvm_vcore)
2696			pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
2697}
2698
2699/*
2700 * Check that we are on thread 0 and that any other threads in
2701 * this core are off-line.  Then grab the threads so they can't
2702 * enter the kernel.
2703 */
2704static int on_primary_thread(void)
2705{
2706	int cpu = smp_processor_id();
2707	int thr;
2708
2709	/* Are we on a primary subcore? */
2710	if (cpu_thread_in_subcore(cpu))
2711		return 0;
2712
2713	thr = 0;
2714	while (++thr < threads_per_subcore)
2715		if (cpu_online(cpu + thr))
2716			return 0;
2717
2718	/* Grab all hw threads so they can't go into the kernel */
2719	for (thr = 1; thr < threads_per_subcore; ++thr) {
2720		if (kvmppc_grab_hwthread(cpu + thr)) {
2721			/* Couldn't grab one; let the others go */
2722			do {
2723				kvmppc_release_hwthread(cpu + thr);
2724			} while (--thr > 0);
2725			return 0;
2726		}
2727	}
2728	return 1;
2729}
2730
2731/*
2732 * A list of virtual cores for each physical CPU.
2733 * These are vcores that could run but their runner VCPU tasks are
2734 * (or may be) preempted.
2735 */
2736struct preempted_vcore_list {
2737	struct list_head	list;
2738	spinlock_t		lock;
2739};
2740
2741static DEFINE_PER_CPU(struct preempted_vcore_list, preempted_vcores);
2742
2743static void init_vcore_lists(void)
2744{
2745	int cpu;
2746
2747	for_each_possible_cpu(cpu) {
2748		struct preempted_vcore_list *lp = &per_cpu(preempted_vcores, cpu);
2749		spin_lock_init(&lp->lock);
2750		INIT_LIST_HEAD(&lp->list);
2751	}
2752}
2753
2754static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc)
2755{
2756	struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores);
2757
2758	vc->vcore_state = VCORE_PREEMPT;
2759	vc->pcpu = smp_processor_id();
2760	if (vc->num_threads < threads_per_vcore(vc->kvm)) {
2761		spin_lock(&lp->lock);
2762		list_add_tail(&vc->preempt_list, &lp->list);
2763		spin_unlock(&lp->lock);
2764	}
2765
2766	/* Start accumulating stolen time */
2767	kvmppc_core_start_stolen(vc);
2768}
2769
2770static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc)
2771{
2772	struct preempted_vcore_list *lp;
2773
2774	kvmppc_core_end_stolen(vc);
2775	if (!list_empty(&vc->preempt_list)) {
2776		lp = &per_cpu(preempted_vcores, vc->pcpu);
2777		spin_lock(&lp->lock);
2778		list_del_init(&vc->preempt_list);
2779		spin_unlock(&lp->lock);
2780	}
2781	vc->vcore_state = VCORE_INACTIVE;
2782}
2783
2784/*
2785 * This stores information about the virtual cores currently
2786 * assigned to a physical core.
2787 */
2788struct core_info {
2789	int		n_subcores;
2790	int		max_subcore_threads;
2791	int		total_threads;
2792	int		subcore_threads[MAX_SUBCORES];
2793	struct kvmppc_vcore *vc[MAX_SUBCORES];
2794};
2795
2796/*
2797 * This mapping means subcores 0 and 1 can use threads 0-3 and 4-7
2798 * respectively in 2-way micro-threading (split-core) mode on POWER8.
2799 */
2800static int subcore_thread_map[MAX_SUBCORES] = { 0, 4, 2, 6 };
2801
2802static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc)
2803{
2804	memset(cip, 0, sizeof(*cip));
2805	cip->n_subcores = 1;
2806	cip->max_subcore_threads = vc->num_threads;
2807	cip->total_threads = vc->num_threads;
2808	cip->subcore_threads[0] = vc->num_threads;
2809	cip->vc[0] = vc;
2810}
2811
2812static bool subcore_config_ok(int n_subcores, int n_threads)
2813{
2814	/*
2815	 * POWER9 "SMT4" cores are permanently in what is effectively a 4-way
2816	 * split-core mode, with one thread per subcore.
2817	 */
2818	if (cpu_has_feature(CPU_FTR_ARCH_300))
2819		return n_subcores <= 4 && n_threads == 1;
2820
2821	/* On POWER8, can only dynamically split if unsplit to begin with */
2822	if (n_subcores > 1 && threads_per_subcore < MAX_SMT_THREADS)
2823		return false;
2824	if (n_subcores > MAX_SUBCORES)
2825		return false;
2826	if (n_subcores > 1) {
2827		if (!(dynamic_mt_modes & 2))
2828			n_subcores = 4;
2829		if (n_subcores > 2 && !(dynamic_mt_modes & 4))
2830			return false;
2831	}
2832
2833	return n_subcores * roundup_pow_of_two(n_threads) <= MAX_SMT_THREADS;
2834}
2835
2836static void init_vcore_to_run(struct kvmppc_vcore *vc)
2837{
2838	vc->entry_exit_map = 0;
2839	vc->in_guest = 0;
2840	vc->napping_threads = 0;
2841	vc->conferring_threads = 0;
2842	vc->tb_offset_applied = 0;
2843}
2844
2845static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
2846{
2847	int n_threads = vc->num_threads;
2848	int sub;
2849
2850	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
2851		return false;
2852
2853	/* In one_vm_per_core mode, require all vcores to be from the same vm */
2854	if (one_vm_per_core && vc->kvm != cip->vc[0]->kvm)
2855		return false;
2856
2857	/* Some POWER9 chips require all threads to be in the same MMU mode */
2858	if (no_mixing_hpt_and_radix &&
2859	    kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm))
2860		return false;
2861
2862	if (n_threads < cip->max_subcore_threads)
2863		n_threads = cip->max_subcore_threads;
2864	if (!subcore_config_ok(cip->n_subcores + 1, n_threads))
2865		return false;
2866	cip->max_subcore_threads = n_threads;
2867
2868	sub = cip->n_subcores;
2869	++cip->n_subcores;
2870	cip->total_threads += vc->num_threads;
2871	cip->subcore_threads[sub] = vc->num_threads;
2872	cip->vc[sub] = vc;
2873	init_vcore_to_run(vc);
2874	list_del_init(&vc->preempt_list);
2875
2876	return true;
2877}
2878
2879/*
2880 * Work out whether it is possible to piggyback the execution of
2881 * vcore *pvc onto the execution of the other vcores described in *cip.
2882 */
2883static bool can_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip,
2884			  int target_threads)
2885{
2886	if (cip->total_threads + pvc->num_threads > target_threads)
2887		return false;
2888
2889	return can_dynamic_split(pvc, cip);
2890}
2891
2892static void prepare_threads(struct kvmppc_vcore *vc)
2893{
2894	int i;
2895	struct kvm_vcpu *vcpu;
2896
2897	for_each_runnable_thread(i, vcpu, vc) {
2898		if (signal_pending(vcpu->arch.run_task))
2899			vcpu->arch.ret = -EINTR;
2900		else if (vcpu->arch.vpa.update_pending ||
2901			 vcpu->arch.slb_shadow.update_pending ||
2902			 vcpu->arch.dtl.update_pending)
2903			vcpu->arch.ret = RESUME_GUEST;
2904		else
2905			continue;
2906		kvmppc_remove_runnable(vc, vcpu);
2907		wake_up(&vcpu->arch.cpu_run);
2908	}
2909}
2910
2911static void collect_piggybacks(struct core_info *cip, int target_threads)
2912{
2913	struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores);
2914	struct kvmppc_vcore *pvc, *vcnext;
2915
2916	spin_lock(&lp->lock);
2917	list_for_each_entry_safe(pvc, vcnext, &lp->list, preempt_list) {
2918		if (!spin_trylock(&pvc->lock))
2919			continue;
2920		prepare_threads(pvc);
2921		if (!pvc->n_runnable || !pvc->kvm->arch.mmu_ready) {
2922			list_del_init(&pvc->preempt_list);
2923			if (pvc->runner == NULL) {
2924				pvc->vcore_state = VCORE_INACTIVE;
2925				kvmppc_core_end_stolen(pvc);
2926			}
2927			spin_unlock(&pvc->lock);
2928			continue;
2929		}
2930		if (!can_piggyback(pvc, cip, target_threads)) {
2931			spin_unlock(&pvc->lock);
2932			continue;
2933		}
2934		kvmppc_core_end_stolen(pvc);
2935		pvc->vcore_state = VCORE_PIGGYBACK;
2936		if (cip->total_threads >= target_threads)
2937			break;
2938	}
2939	spin_unlock(&lp->lock);
2940}
2941
2942static bool recheck_signals_and_mmu(struct core_info *cip)
2943{
2944	int sub, i;
2945	struct kvm_vcpu *vcpu;
2946	struct kvmppc_vcore *vc;
2947
2948	for (sub = 0; sub < cip->n_subcores; ++sub) {
2949		vc = cip->vc[sub];
2950		if (!vc->kvm->arch.mmu_ready)
2951			return true;
2952		for_each_runnable_thread(i, vcpu, vc)
2953			if (signal_pending(vcpu->arch.run_task))
2954				return true;
2955	}
2956	return false;
2957}
2958
2959static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
2960{
2961	int still_running = 0, i;
2962	u64 now;
2963	long ret;
2964	struct kvm_vcpu *vcpu;
2965
2966	spin_lock(&vc->lock);
2967	now = get_tb();
2968	for_each_runnable_thread(i, vcpu, vc) {
2969		/*
2970		 * It's safe to unlock the vcore in the loop here, because
2971		 * for_each_runnable_thread() is safe against removal of
2972		 * the vcpu, and the vcore state is VCORE_EXITING here,
2973		 * so any vcpus becoming runnable will have their arch.trap
2974		 * set to zero and can't actually run in the guest.
2975		 */
2976		spin_unlock(&vc->lock);
2977		/* cancel pending dec exception if dec is positive */
2978		if (now < vcpu->arch.dec_expires &&
2979		    kvmppc_core_pending_dec(vcpu))
2980			kvmppc_core_dequeue_dec(vcpu);
2981
2982		trace_kvm_guest_exit(vcpu);
2983
2984		ret = RESUME_GUEST;
2985		if (vcpu->arch.trap)
2986			ret = kvmppc_handle_exit_hv(vcpu,
2987						    vcpu->arch.run_task);
2988
2989		vcpu->arch.ret = ret;
2990		vcpu->arch.trap = 0;
2991
2992		spin_lock(&vc->lock);
2993		if (is_kvmppc_resume_guest(vcpu->arch.ret)) {
2994			if (vcpu->arch.pending_exceptions)
2995				kvmppc_core_prepare_to_enter(vcpu);
2996			if (vcpu->arch.ceded)
2997				kvmppc_set_timer(vcpu);
2998			else
2999				++still_running;
3000		} else {
3001			kvmppc_remove_runnable(vc, vcpu);
3002			wake_up(&vcpu->arch.cpu_run);
3003		}
3004	}
3005	if (!is_master) {
3006		if (still_running > 0) {
3007			kvmppc_vcore_preempt(vc);
3008		} else if (vc->runner) {
3009			vc->vcore_state = VCORE_PREEMPT;
3010			kvmppc_core_start_stolen(vc);
3011		} else {
3012			vc->vcore_state = VCORE_INACTIVE;
3013		}
3014		if (vc->n_runnable > 0 && vc->runner == NULL) {
3015			/* make sure there's a candidate runner awake */
3016			i = -1;
3017			vcpu = next_runnable_thread(vc, &i);
3018			wake_up(&vcpu->arch.cpu_run);
3019		}
3020	}
3021	spin_unlock(&vc->lock);
3022}
3023
3024/*
3025 * Clear core from the list of active host cores as we are about to
3026 * enter the guest. Only do this if it is the primary thread of the
3027 * core (not if a subcore) that is entering the guest.
3028 */
3029static inline int kvmppc_clear_host_core(unsigned int cpu)
3030{
3031	int core;
3032
3033	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
3034		return 0;
3035	/*
3036	 * Memory barrier can be omitted here as we will do a smp_wmb()
3037	 * later in kvmppc_start_thread and we need ensure that state is
3038	 * visible to other CPUs only after we enter guest.
3039	 */
3040	core = cpu >> threads_shift;
3041	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0;
3042	return 0;
3043}
3044
3045/*
3046 * Advertise this core as an active host core since we exited the guest
3047 * Only need to do this if it is the primary thread of the core that is
3048 * exiting.
3049 */
3050static inline int kvmppc_set_host_core(unsigned int cpu)
3051{
3052	int core;
3053
3054	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
3055		return 0;
3056
3057	/*
3058	 * Memory barrier can be omitted here because we do a spin_unlock
3059	 * immediately after this which provides the memory barrier.
3060	 */
3061	core = cpu >> threads_shift;
3062	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1;
3063	return 0;
3064}
3065
3066static void set_irq_happened(int trap)
3067{
3068	switch (trap) {
3069	case BOOK3S_INTERRUPT_EXTERNAL:
3070		local_paca->irq_happened |= PACA_IRQ_EE;
3071		break;
3072	case BOOK3S_INTERRUPT_H_DOORBELL:
3073		local_paca->irq_happened |= PACA_IRQ_DBELL;
3074		break;
3075	case BOOK3S_INTERRUPT_HMI:
3076		local_paca->irq_happened |= PACA_IRQ_HMI;
3077		break;
3078	case BOOK3S_INTERRUPT_SYSTEM_RESET:
3079		replay_system_reset();
3080		break;
3081	}
3082}
3083
3084/*
3085 * Run a set of guest threads on a physical core.
3086 * Called with vc->lock held.
3087 */
3088static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
3089{
3090	struct kvm_vcpu *vcpu;
3091	int i;
3092	int srcu_idx;
3093	struct core_info core_info;
3094	struct kvmppc_vcore *pvc;
3095	struct kvm_split_mode split_info, *sip;
3096	int split, subcore_size, active;
3097	int sub;
3098	bool thr0_done;
3099	unsigned long cmd_bit, stat_bit;
3100	int pcpu, thr;
3101	int target_threads;
3102	int controlled_threads;
3103	int trap;
3104	bool is_power8;
3105	bool hpt_on_radix;
3106
3107	/*
3108	 * Remove from the list any threads that have a signal pending
3109	 * or need a VPA update done
3110	 */
3111	prepare_threads(vc);
3112
3113	/* if the runner is no longer runnable, let the caller pick a new one */
3114	if (vc->runner->arch.state != KVMPPC_VCPU_RUNNABLE)
3115		return;
3116
3117	/*
3118	 * Initialize *vc.
3119	 */
3120	init_vcore_to_run(vc);
3121	vc->preempt_tb = TB_NIL;
3122
3123	/*
3124	 * Number of threads that we will be controlling: the same as
3125	 * the number of threads per subcore, except on POWER9,
3126	 * where it's 1 because the threads are (mostly) independent.
3127	 */
3128	controlled_threads = threads_per_vcore(vc->kvm);
3129
3130	/*
3131	 * Make sure we are running on primary threads, and that secondary
3132	 * threads are offline.  Also check if the number of threads in this
3133	 * guest are greater than the current system threads per guest.
3134	 * On POWER9, we need to be not in independent-threads mode if
3135	 * this is a HPT guest on a radix host machine where the
3136	 * CPU threads may not be in different MMU modes.
3137	 */
3138	hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() &&
3139		!kvm_is_radix(vc->kvm);
3140	if (((controlled_threads > 1) &&
3141	     ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) ||
3142	    (hpt_on_radix && vc->kvm->arch.threads_indep)) {
3143		for_each_runnable_thread(i, vcpu, vc) {
3144			vcpu->arch.ret = -EBUSY;
3145			kvmppc_remove_runnable(vc, vcpu);
3146			wake_up(&vcpu->arch.cpu_run);
3147		}
3148		goto out;
3149	}
3150
3151	/*
3152	 * See if we could run any other vcores on the physical core
3153	 * along with this one.
3154	 */
3155	init_core_info(&core_info, vc);
3156	pcpu = smp_processor_id();
3157	target_threads = controlled_threads;
3158	if (target_smt_mode && target_smt_mode < target_threads)
3159		target_threads = target_smt_mode;
3160	if (vc->num_threads < target_threads)
3161		collect_piggybacks(&core_info, target_threads);
3162
3163	/*
3164	 * On radix, arrange for TLB flushing if necessary.
3165	 * This has to be done before disabling interrupts since
3166	 * it uses smp_call_function().
3167	 */
3168	pcpu = smp_processor_id();
3169	if (kvm_is_radix(vc->kvm)) {
3170		for (sub = 0; sub < core_info.n_subcores; ++sub)
3171			for_each_runnable_thread(i, vcpu, core_info.vc[sub])
3172				kvmppc_prepare_radix_vcpu(vcpu, pcpu);
3173	}
3174
3175	/*
3176	 * Hard-disable interrupts, and check resched flag and signals.
3177	 * If we need to reschedule or deliver a signal, clean up
3178	 * and return without going into the guest(s).
3179	 * If the mmu_ready flag has been cleared, don't go into the
3180	 * guest because that means a HPT resize operation is in progress.
3181	 */
3182	local_irq_disable();
3183	hard_irq_disable();
3184	if (lazy_irq_pending() || need_resched() ||
3185	    recheck_signals_and_mmu(&core_info)) {
3186		local_irq_enable();
3187		vc->vcore_state = VCORE_INACTIVE;
3188		/* Unlock all except the primary vcore */
3189		for (sub = 1; sub < core_info.n_subcores; ++sub) {
3190			pvc = core_info.vc[sub];
3191			/* Put back on to the preempted vcores list */
3192			kvmppc_vcore_preempt(pvc);
3193			spin_unlock(&pvc->lock);
3194		}
3195		for (i = 0; i < controlled_threads; ++i)
3196			kvmppc_release_hwthread(pcpu + i);
3197		return;
3198	}
3199
3200	kvmppc_clear_host_core(pcpu);
3201
3202	/* Decide on micro-threading (split-core) mode */
3203	subcore_size = threads_per_subcore;
3204	cmd_bit = stat_bit = 0;
3205	split = core_info.n_subcores;
3206	sip = NULL;
3207	is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S)
3208		&& !cpu_has_feature(CPU_FTR_ARCH_300);
3209
3210	if (split > 1 || hpt_on_radix) {
3211		sip = &split_info;
3212		memset(&split_info, 0, sizeof(split_info));
3213		for (sub = 0; sub < core_info.n_subcores; ++sub)
3214			split_info.vc[sub] = core_info.vc[sub];
3215
3216		if (is_power8) {
3217			if (split == 2 && (dynamic_mt_modes & 2)) {
3218				cmd_bit = HID0_POWER8_1TO2LPAR;
3219				stat_bit = HID0_POWER8_2LPARMODE;
3220			} else {
3221				split = 4;
3222				cmd_bit = HID0_POWER8_1TO4LPAR;
3223				stat_bit = HID0_POWER8_4LPARMODE;
3224			}
3225			subcore_size = MAX_SMT_THREADS / split;
3226			split_info.rpr = mfspr(SPRN_RPR);
3227			split_info.pmmar = mfspr(SPRN_PMMAR);
3228			split_info.ldbar = mfspr(SPRN_LDBAR);
3229			split_info.subcore_size = subcore_size;
3230		} else {
3231			split_info.subcore_size = 1;
3232			if (hpt_on_radix) {
3233				/* Use the split_info for LPCR/LPIDR changes */
3234				split_info.lpcr_req = vc->lpcr;
3235				split_info.lpidr_req = vc->kvm->arch.lpid;
3236				split_info.host_lpcr = vc->kvm->arch.host_lpcr;
3237				split_info.do_set = 1;
3238			}
3239		}
3240
3241		/* order writes to split_info before kvm_split_mode pointer */
3242		smp_wmb();
3243	}
3244
3245	for (thr = 0; thr < controlled_threads; ++thr) {
3246		struct paca_struct *paca = paca_ptrs[pcpu + thr];
3247
3248		paca->kvm_hstate.tid = thr;
3249		paca->kvm_hstate.napping = 0;
3250		paca->kvm_hstate.kvm_split_mode = sip;
3251	}
3252
3253	/* Initiate micro-threading (split-core) on POWER8 if required */
3254	if (cmd_bit) {
3255		unsigned long hid0 = mfspr(SPRN_HID0);
3256
3257		hid0 |= cmd_bit | HID0_POWER8_DYNLPARDIS;
3258		mb();
3259		mtspr(SPRN_HID0, hid0);
3260		isync();
3261		for (;;) {
3262			hid0 = mfspr(SPRN_HID0);
3263			if (hid0 & stat_bit)
3264				break;
3265			cpu_relax();
3266		}
3267	}
3268
3269	/*
3270	 * On POWER8, set RWMR register.
3271	 * Since it only affects PURR and SPURR, it doesn't affect
3272	 * the host, so we don't save/restore the host value.
3273	 */
3274	if (is_power8) {
3275		unsigned long rwmr_val = RWMR_RPA_P8_8THREAD;
3276		int n_online = atomic_read(&vc->online_count);
3277
3278		/*
3279		 * Use the 8-thread value if we're doing split-core
3280		 * or if the vcore's online count looks bogus.
3281		 */
3282		if (split == 1 && threads_per_subcore == MAX_SMT_THREADS &&
3283		    n_online >= 1 && n_online <= MAX_SMT_THREADS)
3284			rwmr_val = p8_rwmr_values[n_online];
3285		mtspr(SPRN_RWMR, rwmr_val);
3286	}
3287
3288	/* Start all the threads */
3289	active = 0;
3290	for (sub = 0; sub < core_info.n_subcores; ++sub) {
3291		thr = is_power8 ? subcore_thread_map[sub] : sub;
3292		thr0_done = false;
3293		active |= 1 << thr;
3294		pvc = core_info.vc[sub];
3295		pvc->pcpu = pcpu + thr;
3296		for_each_runnable_thread(i, vcpu, pvc) {
3297			kvmppc_start_thread(vcpu, pvc);
3298			kvmppc_create_dtl_entry(vcpu, pvc);
3299			trace_kvm_guest_enter(vcpu);
3300			if (!vcpu->arch.ptid)
3301				thr0_done = true;
3302			active |= 1 << (thr + vcpu->arch.ptid);
3303		}
3304		/*
3305		 * We need to start the first thread of each subcore
3306		 * even if it doesn't have a vcpu.
3307		 */
3308		if (!thr0_done)
3309			kvmppc_start_thread(NULL, pvc);
3310	}
3311
3312	/*
3313	 * Ensure that split_info.do_nap is set after setting
3314	 * the vcore pointer in the PACA of the secondaries.
3315	 */
3316	smp_mb();
3317
3318	/*
3319	 * When doing micro-threading, poke the inactive threads as well.
3320	 * This gets them to the nap instruction after kvm_do_nap,
3321	 * which reduces the time taken to unsplit later.
3322	 * For POWER9 HPT guest on radix host, we need all the secondary
3323	 * threads woken up so they can do the LPCR/LPIDR change.
3324	 */
3325	if (cmd_bit || hpt_on_radix) {
3326		split_info.do_nap = 1;	/* ask secondaries to nap when done */
3327		for (thr = 1; thr < threads_per_subcore; ++thr)
3328			if (!(active & (1 << thr)))
3329				kvmppc_ipi_thread(pcpu + thr);
3330	}
3331
3332	vc->vcore_state = VCORE_RUNNING;
3333	preempt_disable();
3334
3335	trace_kvmppc_run_core(vc, 0);
3336
3337	for (sub = 0; sub < core_info.n_subcores; ++sub)
3338		spin_unlock(&core_info.vc[sub]->lock);
3339
3340	guest_enter_irqoff();
3341
3342	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
3343
3344	this_cpu_disable_ftrace();
3345
3346	/*
3347	 * Interrupts will be enabled once we get into the guest,
3348	 * so tell lockdep that we're about to enable interrupts.
3349	 */
3350	trace_hardirqs_on();
3351
3352	trap = __kvmppc_vcore_entry();
3353
3354	trace_hardirqs_off();
3355
3356	this_cpu_enable_ftrace();
3357
3358	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
3359
3360	set_irq_happened(trap);
3361
3362	spin_lock(&vc->lock);
3363	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
3364	vc->vcore_state = VCORE_EXITING;
3365
3366	/* wait for secondary threads to finish writing their state to memory */
3367	kvmppc_wait_for_nap(controlled_threads);
3368
3369	/* Return to whole-core mode if we split the core earlier */
3370	if (cmd_bit) {
3371		unsigned long hid0 = mfspr(SPRN_HID0);
3372		unsigned long loops = 0;
3373
3374		hid0 &= ~HID0_POWER8_DYNLPARDIS;
3375		stat_bit = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE;
3376		mb();
3377		mtspr(SPRN_HID0, hid0);
3378		isync();
3379		for (;;) {
3380			hid0 = mfspr(SPRN_HID0);
3381			if (!(hid0 & stat_bit))
3382				break;
3383			cpu_relax();
3384			++loops;
3385		}
3386	} else if (hpt_on_radix) {
3387		/* Wait for all threads to have seen final sync */
3388		for (thr = 1; thr < controlled_threads; ++thr) {
3389			struct paca_struct *paca = paca_ptrs[pcpu + thr];
3390
3391			while (paca->kvm_hstate.kvm_split_mode) {
3392				HMT_low();
3393				barrier();
3394			}
3395			HMT_medium();
3396		}
3397	}
3398	split_info.do_nap = 0;
3399
3400	kvmppc_set_host_core(pcpu);
3401
3402	context_tracking_guest_exit();
3403	if (!vtime_accounting_enabled_this_cpu()) {
3404		local_irq_enable();
3405		/*
3406		 * Service IRQs here before vtime_account_guest_exit() so any
3407		 * ticks that occurred while running the guest are accounted to
3408		 * the guest. If vtime accounting is enabled, accounting uses
3409		 * TB rather than ticks, so it can be done without enabling
3410		 * interrupts here, which has the problem that it accounts
3411		 * interrupt processing overhead to the host.
3412		 */
3413		local_irq_disable();
3414	}
3415	vtime_account_guest_exit();
3416
3417	local_irq_enable();
3418
3419	/* Let secondaries go back to the offline loop */
3420	for (i = 0; i < controlled_threads; ++i) {
3421		kvmppc_release_hwthread(pcpu + i);
3422		if (sip && sip->napped[i])
3423			kvmppc_ipi_thread(pcpu + i);
3424		cpumask_clear_cpu(pcpu + i, &vc->kvm->arch.cpu_in_guest);
3425	}
3426
3427	spin_unlock(&vc->lock);
3428
3429	/* make sure updates to secondary vcpu structs are visible now */
3430	smp_mb();
3431
3432	preempt_enable();
3433
3434	for (sub = 0; sub < core_info.n_subcores; ++sub) {
3435		pvc = core_info.vc[sub];
3436		post_guest_process(pvc, pvc == vc);
3437	}
3438
3439	spin_lock(&vc->lock);
3440
3441 out:
3442	vc->vcore_state = VCORE_INACTIVE;
3443	trace_kvmppc_run_core(vc, 1);
3444}
3445
3446/*
3447 * Load up hypervisor-mode registers on P9.
3448 */
3449static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
3450				     unsigned long lpcr)
3451{
3452	struct kvmppc_vcore *vc = vcpu->arch.vcore;
3453	s64 hdec;
3454	u64 tb, purr, spurr;
3455	int trap;
3456	unsigned long host_hfscr = mfspr(SPRN_HFSCR);
3457	unsigned long host_ciabr = mfspr(SPRN_CIABR);
3458	unsigned long host_dawr = mfspr(SPRN_DAWR0);
3459	unsigned long host_dawrx = mfspr(SPRN_DAWRX0);
3460	unsigned long host_psscr = mfspr(SPRN_PSSCR);
3461	unsigned long host_pidr = mfspr(SPRN_PID);
3462
3463	/*
3464	 * P8 and P9 suppress the HDEC exception when LPCR[HDICE] = 0,
3465	 * so set HDICE before writing HDEC.
3466	 */
3467	mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr | LPCR_HDICE);
3468	isync();
3469
3470	hdec = time_limit - mftb();
3471	if (hdec < 0) {
3472		mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr);
3473		isync();
3474		return BOOK3S_INTERRUPT_HV_DECREMENTER;
3475	}
3476	mtspr(SPRN_HDEC, hdec);
3477
3478	if (vc->tb_offset) {
3479		u64 new_tb = mftb() + vc->tb_offset;
3480		mtspr(SPRN_TBU40, new_tb);
3481		tb = mftb();
3482		if ((tb & 0xffffff) < (new_tb & 0xffffff))
3483			mtspr(SPRN_TBU40, new_tb + 0x1000000);
3484		vc->tb_offset_applied = vc->tb_offset;
3485	}
3486
3487	if (vc->pcr)
3488		mtspr(SPRN_PCR, vc->pcr | PCR_MASK);
3489	mtspr(SPRN_DPDES, vc->dpdes);
3490	mtspr(SPRN_VTB, vc->vtb);
3491
3492	local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR);
3493	local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR);
3494	mtspr(SPRN_PURR, vcpu->arch.purr);
3495	mtspr(SPRN_SPURR, vcpu->arch.spurr);
3496
3497	if (dawr_enabled()) {
3498		mtspr(SPRN_DAWR0, vcpu->arch.dawr);
3499		mtspr(SPRN_DAWRX0, vcpu->arch.dawrx);
3500	}
3501	mtspr(SPRN_CIABR, vcpu->arch.ciabr);
3502	mtspr(SPRN_IC, vcpu->arch.ic);
3503	mtspr(SPRN_PID, vcpu->arch.pid);
3504
3505	mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC |
3506	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
3507
3508	mtspr(SPRN_HFSCR, vcpu->arch.hfscr);
3509
3510	mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0);
3511	mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1);
3512	mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
3513	mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
3514
3515	mtspr(SPRN_AMOR, ~0UL);
3516
3517	mtspr(SPRN_LPCR, lpcr);
3518	isync();
3519
3520	kvmppc_xive_push_vcpu(vcpu);
3521
3522	mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
3523	mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
3524
3525	trap = __kvmhv_vcpu_entry_p9(vcpu);
3526
3527	/* Advance host PURR/SPURR by the amount used by guest */
3528	purr = mfspr(SPRN_PURR);
3529	spurr = mfspr(SPRN_SPURR);
3530	mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr +
3531	      purr - vcpu->arch.purr);
3532	mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr +
3533	      spurr - vcpu->arch.spurr);
3534	vcpu->arch.purr = purr;
3535	vcpu->arch.spurr = spurr;
3536
3537	vcpu->arch.ic = mfspr(SPRN_IC);
3538	vcpu->arch.pid = mfspr(SPRN_PID);
3539	vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS;
3540
3541	vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0);
3542	vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1);
3543	vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
3544	vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
3545
3546	/* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
3547	mtspr(SPRN_PSSCR, host_psscr |
3548	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
3549	mtspr(SPRN_HFSCR, host_hfscr);
3550	mtspr(SPRN_CIABR, host_ciabr);
3551	mtspr(SPRN_DAWR0, host_dawr);
3552	mtspr(SPRN_DAWRX0, host_dawrx);
3553	mtspr(SPRN_PID, host_pidr);
3554
3555	/*
3556	 * Since this is radix, do a eieio; tlbsync; ptesync sequence in
3557	 * case we interrupted the guest between a tlbie and a ptesync.
3558	 */
3559	asm volatile("eieio; tlbsync; ptesync");
3560
3561	/*
3562	 * cp_abort is required if the processor supports local copy-paste
3563	 * to clear the copy buffer that was under control of the guest.
3564	 */
3565	if (cpu_has_feature(CPU_FTR_ARCH_31))
3566		asm volatile(PPC_CP_ABORT);
3567
3568	mtspr(SPRN_LPID, vcpu->kvm->arch.host_lpid);	/* restore host LPID */
3569	isync();
3570
3571	vc->dpdes = mfspr(SPRN_DPDES);
3572	vc->vtb = mfspr(SPRN_VTB);
3573	mtspr(SPRN_DPDES, 0);
3574	if (vc->pcr)
3575		mtspr(SPRN_PCR, PCR_MASK);
3576
3577	if (vc->tb_offset_applied) {
3578		u64 new_tb = mftb() - vc->tb_offset_applied;
3579		mtspr(SPRN_TBU40, new_tb);
3580		tb = mftb();
3581		if ((tb & 0xffffff) < (new_tb & 0xffffff))
3582			mtspr(SPRN_TBU40, new_tb + 0x1000000);
3583		vc->tb_offset_applied = 0;
3584	}
3585
3586	mtspr(SPRN_HDEC, 0x7fffffff);
3587	mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr);
3588
3589	return trap;
3590}
3591
3592/*
3593 * Virtual-mode guest entry for POWER9 and later when the host and
3594 * guest are both using the radix MMU.  The LPIDR has already been set.
3595 */
3596static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
3597			 unsigned long lpcr)
3598{
3599	struct kvmppc_vcore *vc = vcpu->arch.vcore;
3600	unsigned long host_dscr = mfspr(SPRN_DSCR);
3601	unsigned long host_tidr = mfspr(SPRN_TIDR);
3602	unsigned long host_iamr = mfspr(SPRN_IAMR);
3603	unsigned long host_amr = mfspr(SPRN_AMR);
3604	unsigned long host_fscr = mfspr(SPRN_FSCR);
3605	s64 dec;
3606	u64 tb;
3607	int trap, save_pmu;
3608
3609	dec = mfspr(SPRN_DEC);
3610	tb = mftb();
3611	if (dec < 0)
3612		return BOOK3S_INTERRUPT_HV_DECREMENTER;
3613	local_paca->kvm_hstate.dec_expires = dec + tb;
3614	if (local_paca->kvm_hstate.dec_expires < time_limit)
3615		time_limit = local_paca->kvm_hstate.dec_expires;
3616
3617	vcpu->arch.ceded = 0;
3618
3619	kvmhv_save_host_pmu();		/* saves it to PACA kvm_hstate */
3620
3621	kvmppc_subcore_enter_guest();
3622
3623	vc->entry_exit_map = 1;
3624	vc->in_guest = 1;
3625
3626	if (vcpu->arch.vpa.pinned_addr) {
3627		struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
3628		u32 yield_count = be32_to_cpu(lp->yield_count) + 1;
3629		lp->yield_count = cpu_to_be32(yield_count);
3630		vcpu->arch.vpa.dirty = 1;
3631	}
3632
3633	if (cpu_has_feature(CPU_FTR_TM) ||
3634	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
3635		kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
3636
3637#ifdef CONFIG_PPC_PSERIES
3638	if (kvmhv_on_pseries()) {
3639		barrier();
3640		if (vcpu->arch.vpa.pinned_addr) {
3641			struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
3642			get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use;
3643		} else {
3644			get_lppaca()->pmcregs_in_use = 1;
3645		}
3646		barrier();
3647	}
3648#endif
3649	kvmhv_load_guest_pmu(vcpu);
3650
3651	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
3652	load_fp_state(&vcpu->arch.fp);
3653#ifdef CONFIG_ALTIVEC
3654	load_vr_state(&vcpu->arch.vr);
3655#endif
3656	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
3657
3658	mtspr(SPRN_DSCR, vcpu->arch.dscr);
3659	mtspr(SPRN_IAMR, vcpu->arch.iamr);
3660	mtspr(SPRN_PSPB, vcpu->arch.pspb);
3661	mtspr(SPRN_FSCR, vcpu->arch.fscr);
3662	mtspr(SPRN_TAR, vcpu->arch.tar);
3663	mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
3664	mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
3665	mtspr(SPRN_BESCR, vcpu->arch.bescr);
3666	mtspr(SPRN_WORT, vcpu->arch.wort);
3667	mtspr(SPRN_TIDR, vcpu->arch.tid);
3668	mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
3669	mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
3670	mtspr(SPRN_AMR, vcpu->arch.amr);
3671	mtspr(SPRN_UAMOR, vcpu->arch.uamor);
3672
3673	if (!(vcpu->arch.ctrl & 1))
3674		mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
3675
3676	mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb());
3677
3678	if (kvmhv_on_pseries()) {
3679		/*
3680		 * We need to save and restore the guest visible part of the
3681		 * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor
3682		 * doesn't do this for us. Note only required if pseries since
3683		 * this is done in kvmhv_load_hv_regs_and_go() below otherwise.
3684		 */
3685		unsigned long host_psscr;
3686		/* call our hypervisor to load up HV regs and go */
3687		struct hv_guest_state hvregs;
3688
3689		host_psscr = mfspr(SPRN_PSSCR_PR);
3690		mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr);
3691		kvmhv_save_hv_regs(vcpu, &hvregs);
3692		hvregs.lpcr = lpcr;
3693		vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
3694		hvregs.version = HV_GUEST_STATE_VERSION;
3695		if (vcpu->arch.nested) {
3696			hvregs.lpid = vcpu->arch.nested->shadow_lpid;
3697			hvregs.vcpu_token = vcpu->arch.nested_vcpu_id;
3698		} else {
3699			hvregs.lpid = vcpu->kvm->arch.lpid;
3700			hvregs.vcpu_token = vcpu->vcpu_id;
3701		}
3702		hvregs.hdec_expiry = time_limit;
3703		trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs),
3704					  __pa(&vcpu->arch.regs));
3705		kvmhv_restore_hv_return_state(vcpu, &hvregs);
3706		vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
3707		vcpu->arch.shregs.dar = mfspr(SPRN_DAR);
3708		vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);
3709		vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR);
3710		mtspr(SPRN_PSSCR_PR, host_psscr);
3711
3712		/* H_CEDE has to be handled now, not later */
3713		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
3714		    kvmppc_get_gpr(vcpu, 3) == H_CEDE) {
3715			kvmppc_nested_cede(vcpu);
3716			kvmppc_set_gpr(vcpu, 3, 0);
3717			trap = 0;
3718		}
3719	} else {
3720		trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr);
3721	}
3722
3723	vcpu->arch.slb_max = 0;
3724	dec = mfspr(SPRN_DEC);
3725	if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */
3726		dec = (s32) dec;
3727	tb = mftb();
3728	vcpu->arch.dec_expires = dec + tb;
3729	vcpu->cpu = -1;
3730	vcpu->arch.thread_cpu = -1;
3731	/* Save guest CTRL register, set runlatch to 1 */
3732	vcpu->arch.ctrl = mfspr(SPRN_CTRLF);
3733	if (!(vcpu->arch.ctrl & 1))
3734		mtspr(SPRN_CTRLT, vcpu->arch.ctrl | 1);
3735
3736	vcpu->arch.iamr = mfspr(SPRN_IAMR);
3737	vcpu->arch.pspb = mfspr(SPRN_PSPB);
3738	vcpu->arch.fscr = mfspr(SPRN_FSCR);
3739	vcpu->arch.tar = mfspr(SPRN_TAR);
3740	vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
3741	vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
3742	vcpu->arch.bescr = mfspr(SPRN_BESCR);
3743	vcpu->arch.wort = mfspr(SPRN_WORT);
3744	vcpu->arch.tid = mfspr(SPRN_TIDR);
3745	vcpu->arch.amr = mfspr(SPRN_AMR);
3746	vcpu->arch.uamor = mfspr(SPRN_UAMOR);
3747	vcpu->arch.dscr = mfspr(SPRN_DSCR);
3748
3749	mtspr(SPRN_PSPB, 0);
3750	mtspr(SPRN_WORT, 0);
3751	mtspr(SPRN_UAMOR, 0);
3752	mtspr(SPRN_DSCR, host_dscr);
3753	mtspr(SPRN_TIDR, host_tidr);
3754	mtspr(SPRN_IAMR, host_iamr);
3755	mtspr(SPRN_PSPB, 0);
3756
3757	if (host_amr != vcpu->arch.amr)
3758		mtspr(SPRN_AMR, host_amr);
3759
3760	if (host_fscr != vcpu->arch.fscr)
3761		mtspr(SPRN_FSCR, host_fscr);
3762
3763	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
3764	store_fp_state(&vcpu->arch.fp);
3765#ifdef CONFIG_ALTIVEC
3766	store_vr_state(&vcpu->arch.vr);
3767#endif
3768	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
3769
3770	if (cpu_has_feature(CPU_FTR_TM) ||
3771	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
3772		kvmppc_save_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
3773
3774	save_pmu = 1;
3775	if (vcpu->arch.vpa.pinned_addr) {
3776		struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
3777		u32 yield_count = be32_to_cpu(lp->yield_count) + 1;
3778		lp->yield_count = cpu_to_be32(yield_count);
3779		vcpu->arch.vpa.dirty = 1;
3780		save_pmu = lp->pmcregs_in_use;
3781	}
3782	/* Must save pmu if this guest is capable of running nested guests */
3783	save_pmu |= nesting_enabled(vcpu->kvm);
3784
3785	kvmhv_save_guest_pmu(vcpu, save_pmu);
3786#ifdef CONFIG_PPC_PSERIES
3787	if (kvmhv_on_pseries()) {
3788		barrier();
3789		get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse();
3790		barrier();
3791	}
3792#endif
3793
3794	vc->entry_exit_map = 0x101;
3795	vc->in_guest = 0;
3796
3797	mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb());
3798	mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
3799
3800	kvmhv_load_host_pmu();
3801
3802	kvmppc_subcore_exit_guest();
3803
3804	return trap;
3805}
3806
3807/*
3808 * Wait for some other vcpu thread to execute us, and
3809 * wake us up when we need to handle something in the host.
3810 */
3811static void kvmppc_wait_for_exec(struct kvmppc_vcore *vc,
3812				 struct kvm_vcpu *vcpu, int wait_state)
3813{
3814	DEFINE_WAIT(wait);
3815
3816	prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state);
3817	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
3818		spin_unlock(&vc->lock);
3819		schedule();
3820		spin_lock(&vc->lock);
3821	}
3822	finish_wait(&vcpu->arch.cpu_run, &wait);
3823}
3824
3825static void grow_halt_poll_ns(struct kvmppc_vcore *vc)
3826{
3827	if (!halt_poll_ns_grow)
3828		return;
3829
3830	vc->halt_poll_ns *= halt_poll_ns_grow;
3831	if (vc->halt_poll_ns < halt_poll_ns_grow_start)
3832		vc->halt_poll_ns = halt_poll_ns_grow_start;
3833}
3834
3835static void shrink_halt_poll_ns(struct kvmppc_vcore *vc)
3836{
3837	if (halt_poll_ns_shrink == 0)
3838		vc->halt_poll_ns = 0;
3839	else
3840		vc->halt_poll_ns /= halt_poll_ns_shrink;
3841}
3842
3843#ifdef CONFIG_KVM_XICS
3844static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu)
3845{
3846	if (!xics_on_xive())
3847		return false;
3848	return vcpu->arch.irq_pending || vcpu->arch.xive_saved_state.pipr <
3849		vcpu->arch.xive_saved_state.cppr;
3850}
3851#else
3852static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu)
3853{
3854	return false;
3855}
3856#endif /* CONFIG_KVM_XICS */
3857
3858static bool kvmppc_vcpu_woken(struct kvm_vcpu *vcpu)
3859{
3860	if (vcpu->arch.pending_exceptions || vcpu->arch.prodded ||
3861	    kvmppc_doorbell_pending(vcpu) || xive_interrupt_pending(vcpu))
3862		return true;
3863
3864	return false;
3865}
3866
3867/*
3868 * Check to see if any of the runnable vcpus on the vcore have pending
3869 * exceptions or are no longer ceded
3870 */
3871static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc)
3872{
3873	struct kvm_vcpu *vcpu;
3874	int i;
3875
3876	for_each_runnable_thread(i, vcpu, vc) {
3877		if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu))
3878			return 1;
3879	}
3880
3881	return 0;
3882}
3883
3884/*
3885 * All the vcpus in this vcore are idle, so wait for a decrementer
3886 * or external interrupt to one of the vcpus.  vc->lock is held.
3887 */
3888static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
3889{
3890	ktime_t cur, start_poll, start_wait;
3891	int do_sleep = 1;
3892	u64 block_ns;
3893
3894	/* Poll for pending exceptions and ceded state */
3895	cur = start_poll = ktime_get();
3896	if (vc->halt_poll_ns) {
3897		ktime_t stop = ktime_add_ns(start_poll, vc->halt_poll_ns);
3898		++vc->runner->stat.halt_attempted_poll;
3899
3900		vc->vcore_state = VCORE_POLLING;
3901		spin_unlock(&vc->lock);
3902
3903		do {
3904			if (kvmppc_vcore_check_block(vc)) {
3905				do_sleep = 0;
3906				break;
3907			}
3908			cur = ktime_get();
3909		} while (single_task_running() && ktime_before(cur, stop));
3910
3911		spin_lock(&vc->lock);
3912		vc->vcore_state = VCORE_INACTIVE;
3913
3914		if (!do_sleep) {
3915			++vc->runner->stat.halt_successful_poll;
3916			goto out;
3917		}
3918	}
3919
3920	prepare_to_rcuwait(&vc->wait);
3921	set_current_state(TASK_INTERRUPTIBLE);
3922	if (kvmppc_vcore_check_block(vc)) {
3923		finish_rcuwait(&vc->wait);
3924		do_sleep = 0;
3925		/* If we polled, count this as a successful poll */
3926		if (vc->halt_poll_ns)
3927			++vc->runner->stat.halt_successful_poll;
3928		goto out;
3929	}
3930
3931	start_wait = ktime_get();
3932
3933	vc->vcore_state = VCORE_SLEEPING;
3934	trace_kvmppc_vcore_blocked(vc, 0);
3935	spin_unlock(&vc->lock);
3936	schedule();
3937	finish_rcuwait(&vc->wait);
3938	spin_lock(&vc->lock);
3939	vc->vcore_state = VCORE_INACTIVE;
3940	trace_kvmppc_vcore_blocked(vc, 1);
3941	++vc->runner->stat.halt_successful_wait;
3942
3943	cur = ktime_get();
3944
3945out:
3946	block_ns = ktime_to_ns(cur) - ktime_to_ns(start_poll);
3947
3948	/* Attribute wait time */
3949	if (do_sleep) {
3950		vc->runner->stat.halt_wait_ns +=
3951			ktime_to_ns(cur) - ktime_to_ns(start_wait);
3952		/* Attribute failed poll time */
3953		if (vc->halt_poll_ns)
3954			vc->runner->stat.halt_poll_fail_ns +=
3955				ktime_to_ns(start_wait) -
3956				ktime_to_ns(start_poll);
3957	} else {
3958		/* Attribute successful poll time */
3959		if (vc->halt_poll_ns)
3960			vc->runner->stat.halt_poll_success_ns +=
3961				ktime_to_ns(cur) -
3962				ktime_to_ns(start_poll);
3963	}
3964
3965	/* Adjust poll time */
3966	if (halt_poll_ns) {
3967		if (block_ns <= vc->halt_poll_ns)
3968			;
3969		/* We slept and blocked for longer than the max halt time */
3970		else if (vc->halt_poll_ns && block_ns > halt_poll_ns)
3971			shrink_halt_poll_ns(vc);
3972		/* We slept and our poll time is too small */
3973		else if (vc->halt_poll_ns < halt_poll_ns &&
3974				block_ns < halt_poll_ns)
3975			grow_halt_poll_ns(vc);
3976		if (vc->halt_poll_ns > halt_poll_ns)
3977			vc->halt_poll_ns = halt_poll_ns;
3978	} else
3979		vc->halt_poll_ns = 0;
3980
3981	trace_kvmppc_vcore_wakeup(do_sleep, block_ns);
3982}
3983
3984/*
3985 * This never fails for a radix guest, as none of the operations it does
3986 * for a radix guest can fail or have a way to report failure.
3987 * kvmhv_run_single_vcpu() relies on this fact.
3988 */
3989static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu)
3990{
3991	int r = 0;
3992	struct kvm *kvm = vcpu->kvm;
3993
3994	mutex_lock(&kvm->arch.mmu_setup_lock);
3995	if (!kvm->arch.mmu_ready) {
3996		if (!kvm_is_radix(kvm))
3997			r = kvmppc_hv_setup_htab_rma(vcpu);
3998		if (!r) {
3999			if (cpu_has_feature(CPU_FTR_ARCH_300))
4000				kvmppc_setup_partition_table(kvm);
4001			kvm->arch.mmu_ready = 1;
4002		}
4003	}
4004	mutex_unlock(&kvm->arch.mmu_setup_lock);
4005	return r;
4006}
4007
4008static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu)
4009{
4010	struct kvm_run *run = vcpu->run;
4011	int n_ceded, i, r;
4012	struct kvmppc_vcore *vc;
4013	struct kvm_vcpu *v;
4014
4015	trace_kvmppc_run_vcpu_enter(vcpu);
4016
4017	run->exit_reason = 0;
4018	vcpu->arch.ret = RESUME_GUEST;
4019	vcpu->arch.trap = 0;
4020	kvmppc_update_vpas(vcpu);
4021
4022	/*
4023	 * Synchronize with other threads in this virtual core
4024	 */
4025	vc = vcpu->arch.vcore;
4026	spin_lock(&vc->lock);
4027	vcpu->arch.ceded = 0;
4028	vcpu->arch.run_task = current;
4029	vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
4030	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
4031	vcpu->arch.busy_preempt = TB_NIL;
4032	WRITE_ONCE(vc->runnable_threads[vcpu->arch.ptid], vcpu);
4033	++vc->n_runnable;
4034
4035	/*
4036	 * This happens the first time this is called for a vcpu.
4037	 * If the vcore is already running, we may be able to start
4038	 * this thread straight away and have it join in.
4039	 */
4040	if (!signal_pending(current)) {
4041		if ((vc->vcore_state == VCORE_PIGGYBACK ||
4042		     vc->vcore_state == VCORE_RUNNING) &&
4043			   !VCORE_IS_EXITING(vc)) {
4044			kvmppc_create_dtl_entry(vcpu, vc);
4045			kvmppc_start_thread(vcpu, vc);
4046			trace_kvm_guest_enter(vcpu);
4047		} else if (vc->vcore_state == VCORE_SLEEPING) {
4048		        rcuwait_wake_up(&vc->wait);
4049		}
4050
4051	}
4052
4053	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
4054	       !signal_pending(current)) {
4055		/* See if the MMU is ready to go */
4056		if (!vcpu->kvm->arch.mmu_ready) {
4057			spin_unlock(&vc->lock);
4058			r = kvmhv_setup_mmu(vcpu);
4059			spin_lock(&vc->lock);
4060			if (r) {
4061				run->exit_reason = KVM_EXIT_FAIL_ENTRY;
4062				run->fail_entry.
4063					hardware_entry_failure_reason = 0;
4064				vcpu->arch.ret = r;
4065				break;
4066			}
4067		}
4068
4069		if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL)
4070			kvmppc_vcore_end_preempt(vc);
4071
4072		if (vc->vcore_state != VCORE_INACTIVE) {
4073			kvmppc_wait_for_exec(vc, vcpu, TASK_INTERRUPTIBLE);
4074			continue;
4075		}
4076		for_each_runnable_thread(i, v, vc) {
4077			kvmppc_core_prepare_to_enter(v);
4078			if (signal_pending(v->arch.run_task)) {
4079				kvmppc_remove_runnable(vc, v);
4080				v->stat.signal_exits++;
4081				v->run->exit_reason = KVM_EXIT_INTR;
4082				v->arch.ret = -EINTR;
4083				wake_up(&v->arch.cpu_run);
4084			}
4085		}
4086		if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
4087			break;
4088		n_ceded = 0;
4089		for_each_runnable_thread(i, v, vc) {
4090			if (!kvmppc_vcpu_woken(v))
4091				n_ceded += v->arch.ceded;
4092			else
4093				v->arch.ceded = 0;
4094		}
4095		vc->runner = vcpu;
4096		if (n_ceded == vc->n_runnable) {
4097			kvmppc_vcore_blocked(vc);
4098		} else if (need_resched()) {
4099			kvmppc_vcore_preempt(vc);
4100			/* Let something else run */
4101			cond_resched_lock(&vc->lock);
4102			if (vc->vcore_state == VCORE_PREEMPT)
4103				kvmppc_vcore_end_preempt(vc);
4104		} else {
4105			kvmppc_run_core(vc);
4106		}
4107		vc->runner = NULL;
4108	}
4109
4110	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
4111	       (vc->vcore_state == VCORE_RUNNING ||
4112		vc->vcore_state == VCORE_EXITING ||
4113		vc->vcore_state == VCORE_PIGGYBACK))
4114		kvmppc_wait_for_exec(vc, vcpu, TASK_UNINTERRUPTIBLE);
4115
4116	if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL)
4117		kvmppc_vcore_end_preempt(vc);
4118
4119	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
4120		kvmppc_remove_runnable(vc, vcpu);
4121		vcpu->stat.signal_exits++;
4122		run->exit_reason = KVM_EXIT_INTR;
4123		vcpu->arch.ret = -EINTR;
4124	}
4125
4126	if (vc->n_runnable && vc->vcore_state == VCORE_INACTIVE) {
4127		/* Wake up some vcpu to run the core */
4128		i = -1;
4129		v = next_runnable_thread(vc, &i);
4130		wake_up(&v->arch.cpu_run);
4131	}
4132
4133	trace_kvmppc_run_vcpu_exit(vcpu);
4134	spin_unlock(&vc->lock);
4135	return vcpu->arch.ret;
4136}
4137
4138int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
4139			  unsigned long lpcr)
4140{
4141	struct kvm_run *run = vcpu->run;
4142	int trap, r, pcpu;
4143	int srcu_idx, lpid;
4144	struct kvmppc_vcore *vc;
4145	struct kvm *kvm = vcpu->kvm;
4146	struct kvm_nested_guest *nested = vcpu->arch.nested;
4147
4148	trace_kvmppc_run_vcpu_enter(vcpu);
4149
4150	run->exit_reason = 0;
4151	vcpu->arch.ret = RESUME_GUEST;
4152	vcpu->arch.trap = 0;
4153
4154	vc = vcpu->arch.vcore;
4155	vcpu->arch.ceded = 0;
4156	vcpu->arch.run_task = current;
4157	vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
4158	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
4159	vcpu->arch.busy_preempt = TB_NIL;
4160	vcpu->arch.last_inst = KVM_INST_FETCH_FAILED;
4161	vc->runnable_threads[0] = vcpu;
4162	vc->n_runnable = 1;
4163	vc->runner = vcpu;
4164
4165	/* See if the MMU is ready to go */
4166	if (!kvm->arch.mmu_ready)
4167		kvmhv_setup_mmu(vcpu);
4168
4169	if (need_resched())
4170		cond_resched();
4171
4172	kvmppc_update_vpas(vcpu);
4173
4174	init_vcore_to_run(vc);
4175	vc->preempt_tb = TB_NIL;
4176
4177	preempt_disable();
4178	pcpu = smp_processor_id();
4179	vc->pcpu = pcpu;
4180	kvmppc_prepare_radix_vcpu(vcpu, pcpu);
4181
4182	local_irq_disable();
4183	hard_irq_disable();
4184	if (signal_pending(current))
4185		goto sigpend;
4186	if (lazy_irq_pending() || need_resched() || !kvm->arch.mmu_ready)
4187		goto out;
4188
4189	if (!nested) {
4190		kvmppc_core_prepare_to_enter(vcpu);
4191		if (vcpu->arch.doorbell_request) {
4192			vc->dpdes = 1;
4193			smp_wmb();
4194			vcpu->arch.doorbell_request = 0;
4195		}
4196		if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
4197			     &vcpu->arch.pending_exceptions))
4198			lpcr |= LPCR_MER;
4199	} else if (vcpu->arch.pending_exceptions ||
4200		   vcpu->arch.doorbell_request ||
4201		   xive_interrupt_pending(vcpu)) {
4202		vcpu->arch.ret = RESUME_HOST;
4203		goto out;
4204	}
4205
4206	kvmppc_clear_host_core(pcpu);
4207
4208	local_paca->kvm_hstate.tid = 0;
4209	local_paca->kvm_hstate.napping = 0;
4210	local_paca->kvm_hstate.kvm_split_mode = NULL;
4211	kvmppc_start_thread(vcpu, vc);
4212	kvmppc_create_dtl_entry(vcpu, vc);
4213	trace_kvm_guest_enter(vcpu);
4214
4215	vc->vcore_state = VCORE_RUNNING;
4216	trace_kvmppc_run_core(vc, 0);
4217
4218	if (cpu_has_feature(CPU_FTR_HVMODE)) {
4219		lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
4220		mtspr(SPRN_LPID, lpid);
4221		isync();
4222		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
4223	}
4224
4225	guest_enter_irqoff();
4226
4227	srcu_idx = srcu_read_lock(&kvm->srcu);
4228
4229	this_cpu_disable_ftrace();
4230
4231	/* Tell lockdep that we're about to enable interrupts */
4232	trace_hardirqs_on();
4233
4234	trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr);
4235	vcpu->arch.trap = trap;
4236
4237	trace_hardirqs_off();
4238
4239	this_cpu_enable_ftrace();
4240
4241	srcu_read_unlock(&kvm->srcu, srcu_idx);
4242
4243	if (cpu_has_feature(CPU_FTR_HVMODE)) {
4244		mtspr(SPRN_LPID, kvm->arch.host_lpid);
4245		isync();
4246	}
4247
4248	set_irq_happened(trap);
4249
4250	kvmppc_set_host_core(pcpu);
4251
4252	context_tracking_guest_exit();
4253	if (!vtime_accounting_enabled_this_cpu()) {
4254		local_irq_enable();
4255		/*
4256		 * Service IRQs here before vtime_account_guest_exit() so any
4257		 * ticks that occurred while running the guest are accounted to
4258		 * the guest. If vtime accounting is enabled, accounting uses
4259		 * TB rather than ticks, so it can be done without enabling
4260		 * interrupts here, which has the problem that it accounts
4261		 * interrupt processing overhead to the host.
4262		 */
4263		local_irq_disable();
4264	}
4265	vtime_account_guest_exit();
4266
4267	local_irq_enable();
4268
4269	cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest);
4270
4271	preempt_enable();
4272
4273	/*
4274	 * cancel pending decrementer exception if DEC is now positive, or if
4275	 * entering a nested guest in which case the decrementer is now owned
4276	 * by L2 and the L1 decrementer is provided in hdec_expires
4277	 */
4278	if (kvmppc_core_pending_dec(vcpu) &&
4279			((get_tb() < vcpu->arch.dec_expires) ||
4280			 (trap == BOOK3S_INTERRUPT_SYSCALL &&
4281			  kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED)))
4282		kvmppc_core_dequeue_dec(vcpu);
4283
4284	trace_kvm_guest_exit(vcpu);
4285	r = RESUME_GUEST;
4286	if (trap) {
4287		if (!nested)
4288			r = kvmppc_handle_exit_hv(vcpu, current);
4289		else
4290			r = kvmppc_handle_nested_exit(vcpu);
4291	}
4292	vcpu->arch.ret = r;
4293
4294	if (is_kvmppc_resume_guest(r) && vcpu->arch.ceded &&
4295	    !kvmppc_vcpu_woken(vcpu)) {
4296		kvmppc_set_timer(vcpu);
4297		while (vcpu->arch.ceded && !kvmppc_vcpu_woken(vcpu)) {
4298			if (signal_pending(current)) {
4299				vcpu->stat.signal_exits++;
4300				run->exit_reason = KVM_EXIT_INTR;
4301				vcpu->arch.ret = -EINTR;
4302				break;
4303			}
4304			spin_lock(&vc->lock);
4305			kvmppc_vcore_blocked(vc);
4306			spin_unlock(&vc->lock);
4307		}
4308	}
4309	vcpu->arch.ceded = 0;
4310
4311	vc->vcore_state = VCORE_INACTIVE;
4312	trace_kvmppc_run_core(vc, 1);
4313
4314 done:
4315	kvmppc_remove_runnable(vc, vcpu);
4316	trace_kvmppc_run_vcpu_exit(vcpu);
4317
4318	return vcpu->arch.ret;
4319
4320 sigpend:
4321	vcpu->stat.signal_exits++;
4322	run->exit_reason = KVM_EXIT_INTR;
4323	vcpu->arch.ret = -EINTR;
4324 out:
4325	local_irq_enable();
4326	preempt_enable();
4327	goto done;
4328}
4329
4330static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
4331{
4332	struct kvm_run *run = vcpu->run;
4333	int r;
4334	int srcu_idx;
4335	unsigned long ebb_regs[3] = {};	/* shut up GCC */
4336	unsigned long user_tar = 0;
4337	unsigned int user_vrsave;
4338	struct kvm *kvm;
4339
4340	if (!vcpu->arch.sane) {
4341		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
4342		return -EINVAL;
4343	}
4344
4345	/*
4346	 * Don't allow entry with a suspended transaction, because
4347	 * the guest entry/exit code will lose it.
4348	 * If the guest has TM enabled, save away their TM-related SPRs
4349	 * (they will get restored by the TM unavailable interrupt).
4350	 */
4351#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
4352	if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs &&
4353	    (current->thread.regs->msr & MSR_TM)) {
4354		if (MSR_TM_ACTIVE(current->thread.regs->msr)) {
4355			run->exit_reason = KVM_EXIT_FAIL_ENTRY;
4356			run->fail_entry.hardware_entry_failure_reason = 0;
4357			return -EINVAL;
4358		}
4359		/* Enable TM so we can read the TM SPRs */
4360		mtmsr(mfmsr() | MSR_TM);
4361		current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
4362		current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
4363		current->thread.tm_texasr = mfspr(SPRN_TEXASR);
4364		current->thread.regs->msr &= ~MSR_TM;
4365	}
4366#endif
4367
4368	/*
4369	 * Force online to 1 for the sake of old userspace which doesn't
4370	 * set it.
4371	 */
4372	if (!vcpu->arch.online) {
4373		atomic_inc(&vcpu->arch.vcore->online_count);
4374		vcpu->arch.online = 1;
4375	}
4376
4377	kvmppc_core_prepare_to_enter(vcpu);
4378
4379	/* No need to go into the guest when all we'll do is come back out */
4380	if (signal_pending(current)) {
4381		run->exit_reason = KVM_EXIT_INTR;
4382		return -EINTR;
4383	}
4384
4385	kvm = vcpu->kvm;
4386	atomic_inc(&kvm->arch.vcpus_running);
4387	/* Order vcpus_running vs. mmu_ready, see kvmppc_alloc_reset_hpt */
4388	smp_mb();
4389
4390	flush_all_to_thread(current);
4391
4392	/* Save userspace EBB and other register values */
4393	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
4394		ebb_regs[0] = mfspr(SPRN_EBBHR);
4395		ebb_regs[1] = mfspr(SPRN_EBBRR);
4396		ebb_regs[2] = mfspr(SPRN_BESCR);
4397		user_tar = mfspr(SPRN_TAR);
4398	}
4399	user_vrsave = mfspr(SPRN_VRSAVE);
4400
4401	vcpu->arch.waitp = &vcpu->arch.vcore->wait;
4402	vcpu->arch.pgdir = kvm->mm->pgd;
4403	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
4404
4405	do {
4406		/*
4407		 * The early POWER9 chips that can't mix radix and HPT threads
4408		 * on the same core also need the workaround for the problem
4409		 * where the TLB would prefetch entries in the guest exit path
4410		 * for radix guests using the guest PIDR value and LPID 0.
4411		 * The workaround is in the old path (kvmppc_run_vcpu())
4412		 * but not the new path (kvmhv_run_single_vcpu()).
4413		 */
4414		if (kvm->arch.threads_indep && kvm_is_radix(kvm) &&
4415		    !no_mixing_hpt_and_radix)
4416			r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
4417						  vcpu->arch.vcore->lpcr);
4418		else
4419			r = kvmppc_run_vcpu(vcpu);
4420
4421		if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
4422		    !(vcpu->arch.shregs.msr & MSR_PR)) {
4423			trace_kvm_hcall_enter(vcpu);
4424			r = kvmppc_pseries_do_hcall(vcpu);
4425			trace_kvm_hcall_exit(vcpu, r);
4426			kvmppc_core_prepare_to_enter(vcpu);
4427		} else if (r == RESUME_PAGE_FAULT) {
4428			srcu_idx = srcu_read_lock(&kvm->srcu);
4429			r = kvmppc_book3s_hv_page_fault(vcpu,
4430				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
4431			srcu_read_unlock(&kvm->srcu, srcu_idx);
4432		} else if (r == RESUME_PASSTHROUGH) {
4433			if (WARN_ON(xics_on_xive()))
4434				r = H_SUCCESS;
4435			else
4436				r = kvmppc_xics_rm_complete(vcpu, 0);
4437		}
4438	} while (is_kvmppc_resume_guest(r));
4439
4440	/* Restore userspace EBB and other register values */
4441	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
4442		mtspr(SPRN_EBBHR, ebb_regs[0]);
4443		mtspr(SPRN_EBBRR, ebb_regs[1]);
4444		mtspr(SPRN_BESCR, ebb_regs[2]);
4445		mtspr(SPRN_TAR, user_tar);
4446		mtspr(SPRN_FSCR, current->thread.fscr);
4447	}
4448	mtspr(SPRN_VRSAVE, user_vrsave);
4449
4450	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
4451	atomic_dec(&kvm->arch.vcpus_running);
4452	return r;
4453}
4454
4455static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
4456				     int shift, int sllp)
4457{
4458	(*sps)->page_shift = shift;
4459	(*sps)->slb_enc = sllp;
4460	(*sps)->enc[0].page_shift = shift;
4461	(*sps)->enc[0].pte_enc = kvmppc_pgsize_lp_encoding(shift, shift);
4462	/*
4463	 * Add 16MB MPSS support (may get filtered out by userspace)
4464	 */
4465	if (shift != 24) {
4466		int penc = kvmppc_pgsize_lp_encoding(shift, 24);
4467		if (penc != -1) {
4468			(*sps)->enc[1].page_shift = 24;
4469			(*sps)->enc[1].pte_enc = penc;
4470		}
4471	}
4472	(*sps)++;
4473}
4474
4475static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
4476					 struct kvm_ppc_smmu_info *info)
4477{
4478	struct kvm_ppc_one_seg_page_size *sps;
4479
4480	/*
4481	 * POWER7, POWER8 and POWER9 all support 32 storage keys for data.
4482	 * POWER7 doesn't support keys for instruction accesses,
4483	 * POWER8 and POWER9 do.
4484	 */
4485	info->data_keys = 32;
4486	info->instr_keys = cpu_has_feature(CPU_FTR_ARCH_207S) ? 32 : 0;
4487
4488	/* POWER7, 8 and 9 all have 1T segments and 32-entry SLB */
4489	info->flags = KVM_PPC_PAGE_SIZES_REAL | KVM_PPC_1T_SEGMENTS;
4490	info->slb_size = 32;
4491
4492	/* We only support these sizes for now, and no muti-size segments */
4493	sps = &info->sps[0];
4494	kvmppc_add_seg_page_size(&sps, 12, 0);
4495	kvmppc_add_seg_page_size(&sps, 16, SLB_VSID_L | SLB_VSID_LP_01);
4496	kvmppc_add_seg_page_size(&sps, 24, SLB_VSID_L);
4497
4498	/* If running as a nested hypervisor, we don't support HPT guests */
4499	if (kvmhv_on_pseries())
4500		info->flags |= KVM_PPC_NO_HASH;
4501
4502	return 0;
4503}
4504
4505/*
4506 * Get (and clear) the dirty memory log for a memory slot.
4507 */
4508static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
4509					 struct kvm_dirty_log *log)
4510{
4511	struct kvm_memslots *slots;
4512	struct kvm_memory_slot *memslot;
4513	int i, r;
4514	unsigned long n;
4515	unsigned long *buf, *p;
4516	struct kvm_vcpu *vcpu;
4517
4518	mutex_lock(&kvm->slots_lock);
4519
4520	r = -EINVAL;
4521	if (log->slot >= KVM_USER_MEM_SLOTS)
4522		goto out;
4523
4524	slots = kvm_memslots(kvm);
4525	memslot = id_to_memslot(slots, log->slot);
4526	r = -ENOENT;
4527	if (!memslot || !memslot->dirty_bitmap)
4528		goto out;
4529
4530	/*
4531	 * Use second half of bitmap area because both HPT and radix
4532	 * accumulate bits in the first half.
4533	 */
4534	n = kvm_dirty_bitmap_bytes(memslot);
4535	buf = memslot->dirty_bitmap + n / sizeof(long);
4536	memset(buf, 0, n);
4537
4538	if (kvm_is_radix(kvm))
4539		r = kvmppc_hv_get_dirty_log_radix(kvm, memslot, buf);
4540	else
4541		r = kvmppc_hv_get_dirty_log_hpt(kvm, memslot, buf);
4542	if (r)
4543		goto out;
4544
4545	/*
4546	 * We accumulate dirty bits in the first half of the
4547	 * memslot's dirty_bitmap area, for when pages are paged
4548	 * out or modified by the host directly.  Pick up these
4549	 * bits and add them to the map.
4550	 */
4551	p = memslot->dirty_bitmap;
4552	for (i = 0; i < n / sizeof(long); ++i)
4553		buf[i] |= xchg(&p[i], 0);
4554
4555	/* Harvest dirty bits from VPA and DTL updates */
4556	/* Note: we never modify the SLB shadow buffer areas */
4557	kvm_for_each_vcpu(i, vcpu, kvm) {
4558		spin_lock(&vcpu->arch.vpa_update_lock);
4559		kvmppc_harvest_vpa_dirty(&vcpu->arch.vpa, memslot, buf);
4560		kvmppc_harvest_vpa_dirty(&vcpu->arch.dtl, memslot, buf);
4561		spin_unlock(&vcpu->arch.vpa_update_lock);
4562	}
4563
4564	r = -EFAULT;
4565	if (copy_to_user(log->dirty_bitmap, buf, n))
4566		goto out;
4567
4568	r = 0;
4569out:
4570	mutex_unlock(&kvm->slots_lock);
4571	return r;
4572}
4573
4574static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot)
4575{
4576	vfree(slot->arch.rmap);
4577	slot->arch.rmap = NULL;
4578}
4579
4580static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
4581					struct kvm_memory_slot *slot,
4582					const struct kvm_userspace_memory_region *mem,
4583					enum kvm_mr_change change)
4584{
4585	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
4586
4587	if (change == KVM_MR_CREATE) {
4588		unsigned long size = array_size(npages, sizeof(*slot->arch.rmap));
4589
4590		if ((size >> PAGE_SHIFT) > totalram_pages())
4591			return -ENOMEM;
4592
4593		slot->arch.rmap = vzalloc(size);
4594		if (!slot->arch.rmap)
4595			return -ENOMEM;
4596	}
4597
4598	return 0;
4599}
4600
4601static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
4602				const struct kvm_userspace_memory_region *mem,
4603				const struct kvm_memory_slot *old,
4604				const struct kvm_memory_slot *new,
4605				enum kvm_mr_change change)
4606{
4607	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
4608
4609	/*
4610	 * If we are making a new memslot, it might make
4611	 * some address that was previously cached as emulated
4612	 * MMIO be no longer emulated MMIO, so invalidate
4613	 * all the caches of emulated MMIO translations.
4614	 */
4615	if (npages)
4616		atomic64_inc(&kvm->arch.mmio_update);
4617
4618	/*
4619	 * For change == KVM_MR_MOVE or KVM_MR_DELETE, higher levels
4620	 * have already called kvm_arch_flush_shadow_memslot() to
4621	 * flush shadow mappings.  For KVM_MR_CREATE we have no
4622	 * previous mappings.  So the only case to handle is
4623	 * KVM_MR_FLAGS_ONLY when the KVM_MEM_LOG_DIRTY_PAGES bit
4624	 * has been changed.
4625	 * For radix guests, we flush on setting KVM_MEM_LOG_DIRTY_PAGES
4626	 * to get rid of any THP PTEs in the partition-scoped page tables
4627	 * so we can track dirtiness at the page level; we flush when
4628	 * clearing KVM_MEM_LOG_DIRTY_PAGES so that we can go back to
4629	 * using THP PTEs.
4630	 */
4631	if (change == KVM_MR_FLAGS_ONLY && kvm_is_radix(kvm) &&
4632	    ((new->flags ^ old->flags) & KVM_MEM_LOG_DIRTY_PAGES))
4633		kvmppc_radix_flush_memslot(kvm, old);
4634	/*
4635	 * If UV hasn't yet called H_SVM_INIT_START, don't register memslots.
4636	 */
4637	if (!kvm->arch.secure_guest)
4638		return;
4639
4640	switch (change) {
4641	case KVM_MR_CREATE:
4642		/*
4643		 * @TODO kvmppc_uvmem_memslot_create() can fail and
4644		 * return error. Fix this.
4645		 */
4646		kvmppc_uvmem_memslot_create(kvm, new);
4647		break;
4648	case KVM_MR_DELETE:
4649		kvmppc_uvmem_memslot_delete(kvm, old);
4650		break;
4651	default:
4652		/* TODO: Handle KVM_MR_MOVE */
4653		break;
4654	}
4655}
4656
4657/*
4658 * Update LPCR values in kvm->arch and in vcores.
4659 * Caller must hold kvm->arch.mmu_setup_lock (for mutual exclusion
4660 * of kvm->arch.lpcr update).
4661 */
4662void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
4663{
4664	long int i;
4665	u32 cores_done = 0;
4666
4667	if ((kvm->arch.lpcr & mask) == lpcr)
4668		return;
4669
4670	kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr;
4671
4672	for (i = 0; i < KVM_MAX_VCORES; ++i) {
4673		struct kvmppc_vcore *vc = kvm->arch.vcores[i];
4674		if (!vc)
4675			continue;
4676		spin_lock(&vc->lock);
4677		vc->lpcr = (vc->lpcr & ~mask) | lpcr;
4678		spin_unlock(&vc->lock);
4679		if (++cores_done >= kvm->arch.online_vcores)
4680			break;
4681	}
4682}
4683
4684void kvmppc_setup_partition_table(struct kvm *kvm)
4685{
4686	unsigned long dw0, dw1;
4687
4688	if (!kvm_is_radix(kvm)) {
4689		/* PS field - page size for VRMA */
4690		dw0 = ((kvm->arch.vrma_slb_v & SLB_VSID_L) >> 1) |
4691			((kvm->arch.vrma_slb_v & SLB_VSID_LP) << 1);
4692		/* HTABSIZE and HTABORG fields */
4693		dw0 |= kvm->arch.sdr1;
4694
4695		/* Second dword as set by userspace */
4696		dw1 = kvm->arch.process_table;
4697	} else {
4698		dw0 = PATB_HR | radix__get_tree_size() |
4699			__pa(kvm->arch.pgtable) | RADIX_PGD_INDEX_SIZE;
4700		dw1 = PATB_GR | kvm->arch.process_table;
4701	}
4702	kvmhv_set_ptbl_entry(kvm->arch.lpid, dw0, dw1);
4703}
4704
4705/*
4706 * Set up HPT (hashed page table) and RMA (real-mode area).
4707 * Must be called with kvm->arch.mmu_setup_lock held.
4708 */
4709static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
4710{
4711	int err = 0;
4712	struct kvm *kvm = vcpu->kvm;
4713	unsigned long hva;
4714	struct kvm_memory_slot *memslot;
4715	struct vm_area_struct *vma;
4716	unsigned long lpcr = 0, senc;
4717	unsigned long psize, porder;
4718	int srcu_idx;
4719
4720	/* Allocate hashed page table (if not done already) and reset it */
4721	if (!kvm->arch.hpt.virt) {
4722		int order = KVM_DEFAULT_HPT_ORDER;
4723		struct kvm_hpt_info info;
4724
4725		err = kvmppc_allocate_hpt(&info, order);
4726		/* If we get here, it means userspace didn't specify a
4727		 * size explicitly.  So, try successively smaller
4728		 * sizes if the default failed. */
4729		while ((err == -ENOMEM) && --order >= PPC_MIN_HPT_ORDER)
4730			err  = kvmppc_allocate_hpt(&info, order);
4731
4732		if (err < 0) {
4733			pr_err("KVM: Couldn't alloc HPT\n");
4734			goto out;
4735		}
4736
4737		kvmppc_set_hpt(kvm, &info);
4738	}
4739
4740	/* Look up the memslot for guest physical address 0 */
4741	srcu_idx = srcu_read_lock(&kvm->srcu);
4742	memslot = gfn_to_memslot(kvm, 0);
4743
4744	/* We must have some memory at 0 by now */
4745	err = -EINVAL;
4746	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
4747		goto out_srcu;
4748
4749	/* Look up the VMA for the start of this memory slot */
4750	hva = memslot->userspace_addr;
4751	mmap_read_lock(kvm->mm);
4752	vma = find_vma(kvm->mm, hva);
4753	if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO))
4754		goto up_out;
4755
4756	psize = vma_kernel_pagesize(vma);
4757
4758	mmap_read_unlock(kvm->mm);
4759
4760	/* We can handle 4k, 64k or 16M pages in the VRMA */
4761	if (psize >= 0x1000000)
4762		psize = 0x1000000;
4763	else if (psize >= 0x10000)
4764		psize = 0x10000;
4765	else
4766		psize = 0x1000;
4767	porder = __ilog2(psize);
4768
4769	senc = slb_pgsize_encoding(psize);
4770	kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
4771		(VRMA_VSID << SLB_VSID_SHIFT_1T);
4772	/* Create HPTEs in the hash page table for the VRMA */
4773	kvmppc_map_vrma(vcpu, memslot, porder);
4774
4775	/* Update VRMASD field in the LPCR */
4776	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
4777		/* the -4 is to account for senc values starting at 0x10 */
4778		lpcr = senc << (LPCR_VRMASD_SH - 4);
4779		kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
4780	}
4781
4782	/* Order updates to kvm->arch.lpcr etc. vs. mmu_ready */
4783	smp_wmb();
4784	err = 0;
4785 out_srcu:
4786	srcu_read_unlock(&kvm->srcu, srcu_idx);
4787 out:
4788	return err;
4789
4790 up_out:
4791	mmap_read_unlock(kvm->mm);
4792	goto out_srcu;
4793}
4794
4795/*
4796 * Must be called with kvm->arch.mmu_setup_lock held and
4797 * mmu_ready = 0 and no vcpus running.
4798 */
4799int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
4800{
4801	if (nesting_enabled(kvm))
4802		kvmhv_release_all_nested(kvm);
4803	kvmppc_rmap_reset(kvm);
4804	kvm->arch.process_table = 0;
4805	/* Mutual exclusion with kvm_unmap_hva_range etc. */
4806	spin_lock(&kvm->mmu_lock);
4807	kvm->arch.radix = 0;
4808	spin_unlock(&kvm->mmu_lock);
4809	kvmppc_free_radix(kvm);
4810	kvmppc_update_lpcr(kvm, LPCR_VPM1,
4811			   LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR);
4812	return 0;
4813}
4814
4815/*
4816 * Must be called with kvm->arch.mmu_setup_lock held and
4817 * mmu_ready = 0 and no vcpus running.
4818 */
4819int kvmppc_switch_mmu_to_radix(struct kvm *kvm)
4820{
4821	int err;
4822
4823	err = kvmppc_init_vm_radix(kvm);
4824	if (err)
4825		return err;
4826	kvmppc_rmap_reset(kvm);
4827	/* Mutual exclusion with kvm_unmap_hva_range etc. */
4828	spin_lock(&kvm->mmu_lock);
4829	kvm->arch.radix = 1;
4830	spin_unlock(&kvm->mmu_lock);
4831	kvmppc_free_hpt(&kvm->arch.hpt);
4832	kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR,
4833			   LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR);
4834	return 0;
4835}
4836
4837#ifdef CONFIG_KVM_XICS
4838/*
4839 * Allocate a per-core structure for managing state about which cores are
4840 * running in the host versus the guest and for exchanging data between
4841 * real mode KVM and CPU running in the host.
4842 * This is only done for the first VM.
4843 * The allocated structure stays even if all VMs have stopped.
4844 * It is only freed when the kvm-hv module is unloaded.
4845 * It's OK for this routine to fail, we just don't support host
4846 * core operations like redirecting H_IPI wakeups.
4847 */
4848void kvmppc_alloc_host_rm_ops(void)
4849{
4850	struct kvmppc_host_rm_ops *ops;
4851	unsigned long l_ops;
4852	int cpu, core;
4853	int size;
4854
4855	/* Not the first time here ? */
4856	if (kvmppc_host_rm_ops_hv != NULL)
4857		return;
4858
4859	ops = kzalloc(sizeof(struct kvmppc_host_rm_ops), GFP_KERNEL);
4860	if (!ops)
4861		return;
4862
4863	size = cpu_nr_cores() * sizeof(struct kvmppc_host_rm_core);
4864	ops->rm_core = kzalloc(size, GFP_KERNEL);
4865
4866	if (!ops->rm_core) {
4867		kfree(ops);
4868		return;
4869	}
4870
4871	cpus_read_lock();
4872
4873	for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) {
4874		if (!cpu_online(cpu))
4875			continue;
4876
4877		core = cpu >> threads_shift;
4878		ops->rm_core[core].rm_state.in_host = 1;
4879	}
4880
4881	ops->vcpu_kick = kvmppc_fast_vcpu_kick_hv;
4882
4883	/*
4884	 * Make the contents of the kvmppc_host_rm_ops structure visible
4885	 * to other CPUs before we assign it to the global variable.
4886	 * Do an atomic assignment (no locks used here), but if someone
4887	 * beats us to it, just free our copy and return.
4888	 */
4889	smp_wmb();
4890	l_ops = (unsigned long) ops;
4891
4892	if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) {
4893		cpus_read_unlock();
4894		kfree(ops->rm_core);
4895		kfree(ops);
4896		return;
4897	}
4898
4899	cpuhp_setup_state_nocalls_cpuslocked(CPUHP_KVM_PPC_BOOK3S_PREPARE,
4900					     "ppc/kvm_book3s:prepare",
4901					     kvmppc_set_host_core,
4902					     kvmppc_clear_host_core);
4903	cpus_read_unlock();
4904}
4905
4906void kvmppc_free_host_rm_ops(void)
4907{
4908	if (kvmppc_host_rm_ops_hv) {
4909		cpuhp_remove_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE);
4910		kfree(kvmppc_host_rm_ops_hv->rm_core);
4911		kfree(kvmppc_host_rm_ops_hv);
4912		kvmppc_host_rm_ops_hv = NULL;
4913	}
4914}
4915#endif
4916
4917static int kvmppc_core_init_vm_hv(struct kvm *kvm)
4918{
4919	unsigned long lpcr, lpid;
4920	char buf[32];
4921	int ret;
4922
4923	mutex_init(&kvm->arch.uvmem_lock);
4924	INIT_LIST_HEAD(&kvm->arch.uvmem_pfns);
4925	mutex_init(&kvm->arch.mmu_setup_lock);
4926
4927	/* Allocate the guest's logical partition ID */
4928
4929	lpid = kvmppc_alloc_lpid();
4930	if ((long)lpid < 0)
4931		return -ENOMEM;
4932	kvm->arch.lpid = lpid;
4933
4934	kvmppc_alloc_host_rm_ops();
4935
4936	kvmhv_vm_nested_init(kvm);
4937
4938	/*
4939	 * Since we don't flush the TLB when tearing down a VM,
4940	 * and this lpid might have previously been used,
4941	 * make sure we flush on each core before running the new VM.
4942	 * On POWER9, the tlbie in mmu_partition_table_set_entry()
4943	 * does this flush for us.
4944	 */
4945	if (!cpu_has_feature(CPU_FTR_ARCH_300))
4946		cpumask_setall(&kvm->arch.need_tlb_flush);
4947
4948	/* Start out with the default set of hcalls enabled */
4949	memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
4950	       sizeof(kvm->arch.enabled_hcalls));
4951
4952	if (!cpu_has_feature(CPU_FTR_ARCH_300))
4953		kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
4954
4955	/* Init LPCR for virtual RMA mode */
4956	if (cpu_has_feature(CPU_FTR_HVMODE)) {
4957		kvm->arch.host_lpid = mfspr(SPRN_LPID);
4958		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
4959		lpcr &= LPCR_PECE | LPCR_LPES;
4960	} else {
4961		lpcr = 0;
4962	}
4963	lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
4964		LPCR_VPM0 | LPCR_VPM1;
4965	kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
4966		(VRMA_VSID << SLB_VSID_SHIFT_1T);
4967	/* On POWER8 turn on online bit to enable PURR/SPURR */
4968	if (cpu_has_feature(CPU_FTR_ARCH_207S))
4969		lpcr |= LPCR_ONL;
4970	/*
4971	 * On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed)
4972	 * Set HVICE bit to enable hypervisor virtualization interrupts.
4973	 * Set HEIC to prevent OS interrupts to go to hypervisor (should
4974	 * be unnecessary but better safe than sorry in case we re-enable
4975	 * EE in HV mode with this LPCR still set)
4976	 */
4977	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
4978		lpcr &= ~LPCR_VPM0;
4979		lpcr |= LPCR_HVICE | LPCR_HEIC;
4980
4981		/*
4982		 * If xive is enabled, we route 0x500 interrupts directly
4983		 * to the guest.
4984		 */
4985		if (xics_on_xive())
4986			lpcr |= LPCR_LPES;
4987	}
4988
4989	/*
4990	 * If the host uses radix, the guest starts out as radix.
4991	 */
4992	if (radix_enabled()) {
4993		kvm->arch.radix = 1;
4994		kvm->arch.mmu_ready = 1;
4995		lpcr &= ~LPCR_VPM1;
4996		lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR;
4997		ret = kvmppc_init_vm_radix(kvm);
4998		if (ret) {
4999			kvmppc_free_lpid(kvm->arch.lpid);
5000			return ret;
5001		}
5002		kvmppc_setup_partition_table(kvm);
5003	}
5004
5005	kvm->arch.lpcr = lpcr;
5006
5007	/* Initialization for future HPT resizes */
5008	kvm->arch.resize_hpt = NULL;
5009
5010	/*
5011	 * Work out how many sets the TLB has, for the use of
5012	 * the TLB invalidation loop in book3s_hv_rmhandlers.S.
5013	 */
5014	if (radix_enabled())
5015		kvm->arch.tlb_sets = POWER9_TLB_SETS_RADIX;	/* 128 */
5016	else if (cpu_has_feature(CPU_FTR_ARCH_300))
5017		kvm->arch.tlb_sets = POWER9_TLB_SETS_HASH;	/* 256 */
5018	else if (cpu_has_feature(CPU_FTR_ARCH_207S))
5019		kvm->arch.tlb_sets = POWER8_TLB_SETS;		/* 512 */
5020	else
5021		kvm->arch.tlb_sets = POWER7_TLB_SETS;		/* 128 */
5022
5023	/*
5024	 * Track that we now have a HV mode VM active. This blocks secondary
5025	 * CPU threads from coming online.
5026	 * On POWER9, we only need to do this if the "indep_threads_mode"
5027	 * module parameter has been set to N.
5028	 */
5029	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
5030		if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) {
5031			pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n");
5032			kvm->arch.threads_indep = true;
5033		} else {
5034			kvm->arch.threads_indep = indep_threads_mode;
5035		}
5036	}
5037	if (!kvm->arch.threads_indep)
5038		kvm_hv_vm_activated();
5039
5040	/*
5041	 * Initialize smt_mode depending on processor.
5042	 * POWER8 and earlier have to use "strict" threading, where
5043	 * all vCPUs in a vcore have to run on the same (sub)core,
5044	 * whereas on POWER9 the threads can each run a different
5045	 * guest.
5046	 */
5047	if (!cpu_has_feature(CPU_FTR_ARCH_300))
5048		kvm->arch.smt_mode = threads_per_subcore;
5049	else
5050		kvm->arch.smt_mode = 1;
5051	kvm->arch.emul_smt_mode = 1;
5052
5053	/*
5054	 * Create a debugfs directory for the VM
5055	 */
5056	snprintf(buf, sizeof(buf), "vm%d", current->pid);
5057	kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir);
5058	kvmppc_mmu_debugfs_init(kvm);
5059	if (radix_enabled())
5060		kvmhv_radix_debugfs_init(kvm);
5061
5062	return 0;
5063}
5064
5065static void kvmppc_free_vcores(struct kvm *kvm)
5066{
5067	long int i;
5068
5069	for (i = 0; i < KVM_MAX_VCORES; ++i)
5070		kfree(kvm->arch.vcores[i]);
5071	kvm->arch.online_vcores = 0;
5072}
5073
5074static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
5075{
5076	debugfs_remove_recursive(kvm->arch.debugfs_dir);
5077
5078	if (!kvm->arch.threads_indep)
5079		kvm_hv_vm_deactivated();
5080
5081	kvmppc_free_vcores(kvm);
5082
5083
5084	if (kvm_is_radix(kvm))
5085		kvmppc_free_radix(kvm);
5086	else
5087		kvmppc_free_hpt(&kvm->arch.hpt);
5088
5089	/* Perform global invalidation and return lpid to the pool */
5090	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
5091		if (nesting_enabled(kvm))
5092			kvmhv_release_all_nested(kvm);
5093		kvm->arch.process_table = 0;
5094		if (kvm->arch.secure_guest)
5095			uv_svm_terminate(kvm->arch.lpid);
5096		kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
5097	}
5098
5099	kvmppc_free_lpid(kvm->arch.lpid);
5100
5101	kvmppc_free_pimap(kvm);
5102}
5103
5104/* We don't need to emulate any privileged instructions or dcbz */
5105static int kvmppc_core_emulate_op_hv(struct kvm_vcpu *vcpu,
5106				     unsigned int inst, int *advance)
5107{
5108	return EMULATE_FAIL;
5109}
5110
5111static int kvmppc_core_emulate_mtspr_hv(struct kvm_vcpu *vcpu, int sprn,
5112					ulong spr_val)
5113{
5114	return EMULATE_FAIL;
5115}
5116
5117static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn,
5118					ulong *spr_val)
5119{
5120	return EMULATE_FAIL;
5121}
5122
5123static int kvmppc_core_check_processor_compat_hv(void)
5124{
5125	if (cpu_has_feature(CPU_FTR_HVMODE) &&
5126	    cpu_has_feature(CPU_FTR_ARCH_206))
5127		return 0;
5128
5129	/* POWER9 in radix mode is capable of being a nested hypervisor. */
5130	if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled())
5131		return 0;
5132
5133	return -EIO;
5134}
5135
5136#ifdef CONFIG_KVM_XICS
5137
5138void kvmppc_free_pimap(struct kvm *kvm)
5139{
5140	kfree(kvm->arch.pimap);
5141}
5142
5143static struct kvmppc_passthru_irqmap *kvmppc_alloc_pimap(void)
5144{
5145	return kzalloc(sizeof(struct kvmppc_passthru_irqmap), GFP_KERNEL);
5146}
5147
5148static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
5149{
5150	struct irq_desc *desc;
5151	struct kvmppc_irq_map *irq_map;
5152	struct kvmppc_passthru_irqmap *pimap;
5153	struct irq_chip *chip;
5154	int i, rc = 0;
5155
5156	if (!kvm_irq_bypass)
5157		return 1;
5158
5159	desc = irq_to_desc(host_irq);
5160	if (!desc)
5161		return -EIO;
5162
5163	mutex_lock(&kvm->lock);
5164
5165	pimap = kvm->arch.pimap;
5166	if (pimap == NULL) {
5167		/* First call, allocate structure to hold IRQ map */
5168		pimap = kvmppc_alloc_pimap();
5169		if (pimap == NULL) {
5170			mutex_unlock(&kvm->lock);
5171			return -ENOMEM;
5172		}
5173		kvm->arch.pimap = pimap;
5174	}
5175
5176	/*
5177	 * For now, we only support interrupts for which the EOI operation
5178	 * is an OPAL call followed by a write to XIRR, since that's
5179	 * what our real-mode EOI code does, or a XIVE interrupt
5180	 */
5181	chip = irq_data_get_irq_chip(&desc->irq_data);
5182	if (!chip || !(is_pnv_opal_msi(chip) || is_xive_irq(chip))) {
5183		pr_warn("kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (%d,%d)\n",
5184			host_irq, guest_gsi);
5185		mutex_unlock(&kvm->lock);
5186		return -ENOENT;
5187	}
5188
5189	/*
5190	 * See if we already have an entry for this guest IRQ number.
5191	 * If it's mapped to a hardware IRQ number, that's an error,
5192	 * otherwise re-use this entry.
5193	 */
5194	for (i = 0; i < pimap->n_mapped; i++) {
5195		if (guest_gsi == pimap->mapped[i].v_hwirq) {
5196			if (pimap->mapped[i].r_hwirq) {
5197				mutex_unlock(&kvm->lock);
5198				return -EINVAL;
5199			}
5200			break;
5201		}
5202	}
5203
5204	if (i == KVMPPC_PIRQ_MAPPED) {
5205		mutex_unlock(&kvm->lock);
5206		return -EAGAIN;		/* table is full */
5207	}
5208
5209	irq_map = &pimap->mapped[i];
5210
5211	irq_map->v_hwirq = guest_gsi;
5212	irq_map->desc = desc;
5213
5214	/*
5215	 * Order the above two stores before the next to serialize with
5216	 * the KVM real mode handler.
5217	 */
5218	smp_wmb();
5219	irq_map->r_hwirq = desc->irq_data.hwirq;
5220
5221	if (i == pimap->n_mapped)
5222		pimap->n_mapped++;
5223
5224	if (xics_on_xive())
5225		rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc);
5226	else
5227		kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
5228	if (rc)
5229		irq_map->r_hwirq = 0;
5230
5231	mutex_unlock(&kvm->lock);
5232
5233	return 0;
5234}
5235
5236static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
5237{
5238	struct irq_desc *desc;
5239	struct kvmppc_passthru_irqmap *pimap;
5240	int i, rc = 0;
5241
5242	if (!kvm_irq_bypass)
5243		return 0;
5244
5245	desc = irq_to_desc(host_irq);
5246	if (!desc)
5247		return -EIO;
5248
5249	mutex_lock(&kvm->lock);
5250	if (!kvm->arch.pimap)
5251		goto unlock;
5252
5253	pimap = kvm->arch.pimap;
5254
5255	for (i = 0; i < pimap->n_mapped; i++) {
5256		if (guest_gsi == pimap->mapped[i].v_hwirq)
5257			break;
5258	}
5259
5260	if (i == pimap->n_mapped) {
5261		mutex_unlock(&kvm->lock);
5262		return -ENODEV;
5263	}
5264
5265	if (xics_on_xive())
5266		rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc);
5267	else
5268		kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
5269
5270	/* invalidate the entry (what do do on error from the above ?) */
5271	pimap->mapped[i].r_hwirq = 0;
5272
5273	/*
5274	 * We don't free this structure even when the count goes to
5275	 * zero. The structure is freed when we destroy the VM.
5276	 */
5277 unlock:
5278	mutex_unlock(&kvm->lock);
5279	return rc;
5280}
5281
5282static int kvmppc_irq_bypass_add_producer_hv(struct irq_bypass_consumer *cons,
5283					     struct irq_bypass_producer *prod)
5284{
5285	int ret = 0;
5286	struct kvm_kernel_irqfd *irqfd =
5287		container_of(cons, struct kvm_kernel_irqfd, consumer);
5288
5289	irqfd->producer = prod;
5290
5291	ret = kvmppc_set_passthru_irq(irqfd->kvm, prod->irq, irqfd->gsi);
5292	if (ret)
5293		pr_info("kvmppc_set_passthru_irq (irq %d, gsi %d) fails: %d\n",
5294			prod->irq, irqfd->gsi, ret);
5295
5296	return ret;
5297}
5298
5299static void kvmppc_irq_bypass_del_producer_hv(struct irq_bypass_consumer *cons,
5300					      struct irq_bypass_producer *prod)
5301{
5302	int ret;
5303	struct kvm_kernel_irqfd *irqfd =
5304		container_of(cons, struct kvm_kernel_irqfd, consumer);
5305
5306	irqfd->producer = NULL;
5307
5308	/*
5309	 * When producer of consumer is unregistered, we change back to
5310	 * default external interrupt handling mode - KVM real mode
5311	 * will switch back to host.
5312	 */
5313	ret = kvmppc_clr_passthru_irq(irqfd->kvm, prod->irq, irqfd->gsi);
5314	if (ret)
5315		pr_warn("kvmppc_clr_passthru_irq (irq %d, gsi %d) fails: %d\n",
5316			prod->irq, irqfd->gsi, ret);
5317}
5318#endif
5319
5320static long kvm_arch_vm_ioctl_hv(struct file *filp,
5321				 unsigned int ioctl, unsigned long arg)
5322{
5323	struct kvm *kvm __maybe_unused = filp->private_data;
5324	void __user *argp = (void __user *)arg;
5325	long r;
5326
5327	switch (ioctl) {
5328
5329	case KVM_PPC_ALLOCATE_HTAB: {
5330		u32 htab_order;
5331
5332		/* If we're a nested hypervisor, we currently only support radix */
5333		if (kvmhv_on_pseries()) {
5334			r = -EOPNOTSUPP;
5335			break;
5336		}
5337
5338		r = -EFAULT;
5339		if (get_user(htab_order, (u32 __user *)argp))
5340			break;
5341		r = kvmppc_alloc_reset_hpt(kvm, htab_order);
5342		if (r)
5343			break;
5344		r = 0;
5345		break;
5346	}
5347
5348	case KVM_PPC_GET_HTAB_FD: {
5349		struct kvm_get_htab_fd ghf;
5350
5351		r = -EFAULT;
5352		if (copy_from_user(&ghf, argp, sizeof(ghf)))
5353			break;
5354		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
5355		break;
5356	}
5357
5358	case KVM_PPC_RESIZE_HPT_PREPARE: {
5359		struct kvm_ppc_resize_hpt rhpt;
5360
5361		r = -EFAULT;
5362		if (copy_from_user(&rhpt, argp, sizeof(rhpt)))
5363			break;
5364
5365		r = kvm_vm_ioctl_resize_hpt_prepare(kvm, &rhpt);
5366		break;
5367	}
5368
5369	case KVM_PPC_RESIZE_HPT_COMMIT: {
5370		struct kvm_ppc_resize_hpt rhpt;
5371
5372		r = -EFAULT;
5373		if (copy_from_user(&rhpt, argp, sizeof(rhpt)))
5374			break;
5375
5376		r = kvm_vm_ioctl_resize_hpt_commit(kvm, &rhpt);
5377		break;
5378	}
5379
5380	default:
5381		r = -ENOTTY;
5382	}
5383
5384	return r;
5385}
5386
5387/*
5388 * List of hcall numbers to enable by default.
5389 * For compatibility with old userspace, we enable by default
5390 * all hcalls that were implemented before the hcall-enabling
5391 * facility was added.  Note this list should not include H_RTAS.
5392 */
5393static unsigned int default_hcall_list[] = {
5394	H_REMOVE,
5395	H_ENTER,
5396	H_READ,
5397	H_PROTECT,
5398	H_BULK_REMOVE,
5399	H_GET_TCE,
5400	H_PUT_TCE,
5401	H_SET_DABR,
5402	H_SET_XDABR,
5403	H_CEDE,
5404	H_PROD,
5405	H_CONFER,
5406	H_REGISTER_VPA,
5407#ifdef CONFIG_KVM_XICS
5408	H_EOI,
5409	H_CPPR,
5410	H_IPI,
5411	H_IPOLL,
5412	H_XIRR,
5413	H_XIRR_X,
5414#endif
5415	0
5416};
5417
5418static void init_default_hcalls(void)
5419{
5420	int i;
5421	unsigned int hcall;
5422
5423	for (i = 0; default_hcall_list[i]; ++i) {
5424		hcall = default_hcall_list[i];
5425		WARN_ON(!kvmppc_hcall_impl_hv(hcall));
5426		__set_bit(hcall / 4, default_enabled_hcalls);
5427	}
5428}
5429
5430static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
5431{
5432	unsigned long lpcr;
5433	int radix;
5434	int err;
5435
5436	/* If not on a POWER9, reject it */
5437	if (!cpu_has_feature(CPU_FTR_ARCH_300))
5438		return -ENODEV;
5439
5440	/* If any unknown flags set, reject it */
5441	if (cfg->flags & ~(KVM_PPC_MMUV3_RADIX | KVM_PPC_MMUV3_GTSE))
5442		return -EINVAL;
5443
5444	/* GR (guest radix) bit in process_table field must match */
5445	radix = !!(cfg->flags & KVM_PPC_MMUV3_RADIX);
5446	if (!!(cfg->process_table & PATB_GR) != radix)
5447		return -EINVAL;
5448
5449	/* Process table size field must be reasonable, i.e. <= 24 */
5450	if ((cfg->process_table & PRTS_MASK) > 24)
5451		return -EINVAL;
5452
5453	/* We can change a guest to/from radix now, if the host is radix */
5454	if (radix && !radix_enabled())
5455		return -EINVAL;
5456
5457	/* If we're a nested hypervisor, we currently only support radix */
5458	if (kvmhv_on_pseries() && !radix)
5459		return -EINVAL;
5460
5461	mutex_lock(&kvm->arch.mmu_setup_lock);
5462	if (radix != kvm_is_radix(kvm)) {
5463		if (kvm->arch.mmu_ready) {
5464			kvm->arch.mmu_ready = 0;
5465			/* order mmu_ready vs. vcpus_running */
5466			smp_mb();
5467			if (atomic_read(&kvm->arch.vcpus_running)) {
5468				kvm->arch.mmu_ready = 1;
5469				err = -EBUSY;
5470				goto out_unlock;
5471			}
5472		}
5473		if (radix)
5474			err = kvmppc_switch_mmu_to_radix(kvm);
5475		else
5476			err = kvmppc_switch_mmu_to_hpt(kvm);
5477		if (err)
5478			goto out_unlock;
5479	}
5480
5481	kvm->arch.process_table = cfg->process_table;
5482	kvmppc_setup_partition_table(kvm);
5483
5484	lpcr = (cfg->flags & KVM_PPC_MMUV3_GTSE) ? LPCR_GTSE : 0;
5485	kvmppc_update_lpcr(kvm, lpcr, LPCR_GTSE);
5486	err = 0;
5487
5488 out_unlock:
5489	mutex_unlock(&kvm->arch.mmu_setup_lock);
5490	return err;
5491}
5492
5493static int kvmhv_enable_nested(struct kvm *kvm)
5494{
5495	if (!nested)
5496		return -EPERM;
5497	if (!cpu_has_feature(CPU_FTR_ARCH_300) || no_mixing_hpt_and_radix)
5498		return -ENODEV;
5499
5500	/* kvm == NULL means the caller is testing if the capability exists */
5501	if (kvm)
5502		kvm->arch.nested_enable = true;
5503	return 0;
5504}
5505
5506static int kvmhv_load_from_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
5507				 int size)
5508{
5509	int rc = -EINVAL;
5510
5511	if (kvmhv_vcpu_is_radix(vcpu)) {
5512		rc = kvmhv_copy_from_guest_radix(vcpu, *eaddr, ptr, size);
5513
5514		if (rc > 0)
5515			rc = -EINVAL;
5516	}
5517
5518	/* For now quadrants are the only way to access nested guest memory */
5519	if (rc && vcpu->arch.nested)
5520		rc = -EAGAIN;
5521
5522	return rc;
5523}
5524
5525static int kvmhv_store_to_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
5526				int size)
5527{
5528	int rc = -EINVAL;
5529
5530	if (kvmhv_vcpu_is_radix(vcpu)) {
5531		rc = kvmhv_copy_to_guest_radix(vcpu, *eaddr, ptr, size);
5532
5533		if (rc > 0)
5534			rc = -EINVAL;
5535	}
5536
5537	/* For now quadrants are the only way to access nested guest memory */
5538	if (rc && vcpu->arch.nested)
5539		rc = -EAGAIN;
5540
5541	return rc;
5542}
5543
5544static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa)
5545{
5546	unpin_vpa(kvm, vpa);
5547	vpa->gpa = 0;
5548	vpa->pinned_addr = NULL;
5549	vpa->dirty = false;
5550	vpa->update_pending = 0;
5551}
5552
5553/*
5554 * Enable a guest to become a secure VM, or test whether
5555 * that could be enabled.
5556 * Called when the KVM_CAP_PPC_SECURE_GUEST capability is
5557 * tested (kvm == NULL) or enabled (kvm != NULL).
5558 */
5559static int kvmhv_enable_svm(struct kvm *kvm)
5560{
5561	if (!kvmppc_uvmem_available())
5562		return -EINVAL;
5563	if (kvm)
5564		kvm->arch.svm_enabled = 1;
5565	return 0;
5566}
5567
5568/*
5569 *  IOCTL handler to turn off secure mode of guest
5570 *
5571 * - Release all device pages
5572 * - Issue ucall to terminate the guest on the UV side
5573 * - Unpin the VPA pages.
5574 * - Reinit the partition scoped page tables
5575 */
5576static int kvmhv_svm_off(struct kvm *kvm)
5577{
5578	struct kvm_vcpu *vcpu;
5579	int mmu_was_ready;
5580	int srcu_idx;
5581	int ret = 0;
5582	int i;
5583
5584	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
5585		return ret;
5586
5587	mutex_lock(&kvm->arch.mmu_setup_lock);
5588	mmu_was_ready = kvm->arch.mmu_ready;
5589	if (kvm->arch.mmu_ready) {
5590		kvm->arch.mmu_ready = 0;
5591		/* order mmu_ready vs. vcpus_running */
5592		smp_mb();
5593		if (atomic_read(&kvm->arch.vcpus_running)) {
5594			kvm->arch.mmu_ready = 1;
5595			ret = -EBUSY;
5596			goto out;
5597		}
5598	}
5599
5600	srcu_idx = srcu_read_lock(&kvm->srcu);
5601	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
5602		struct kvm_memory_slot *memslot;
5603		struct kvm_memslots *slots = __kvm_memslots(kvm, i);
5604
5605		if (!slots)
5606			continue;
5607
5608		kvm_for_each_memslot(memslot, slots) {
5609			kvmppc_uvmem_drop_pages(memslot, kvm, true);
5610			uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
5611		}
5612	}
5613	srcu_read_unlock(&kvm->srcu, srcu_idx);
5614
5615	ret = uv_svm_terminate(kvm->arch.lpid);
5616	if (ret != U_SUCCESS) {
5617		ret = -EINVAL;
5618		goto out;
5619	}
5620
5621	/*
5622	 * When secure guest is reset, all the guest pages are sent
5623	 * to UV via UV_PAGE_IN before the non-boot vcpus get a
5624	 * chance to run and unpin their VPA pages. Unpinning of all
5625	 * VPA pages is done here explicitly so that VPA pages
5626	 * can be migrated to the secure side.
5627	 *
5628	 * This is required to for the secure SMP guest to reboot
5629	 * correctly.
5630	 */
5631	kvm_for_each_vcpu(i, vcpu, kvm) {
5632		spin_lock(&vcpu->arch.vpa_update_lock);
5633		unpin_vpa_reset(kvm, &vcpu->arch.dtl);
5634		unpin_vpa_reset(kvm, &vcpu->arch.slb_shadow);
5635		unpin_vpa_reset(kvm, &vcpu->arch.vpa);
5636		spin_unlock(&vcpu->arch.vpa_update_lock);
5637	}
5638
5639	kvmppc_setup_partition_table(kvm);
5640	kvm->arch.secure_guest = 0;
5641	kvm->arch.mmu_ready = mmu_was_ready;
5642out:
5643	mutex_unlock(&kvm->arch.mmu_setup_lock);
5644	return ret;
5645}
5646
5647static struct kvmppc_ops kvm_ops_hv = {
5648	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
5649	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
5650	.get_one_reg = kvmppc_get_one_reg_hv,
5651	.set_one_reg = kvmppc_set_one_reg_hv,
5652	.vcpu_load   = kvmppc_core_vcpu_load_hv,
5653	.vcpu_put    = kvmppc_core_vcpu_put_hv,
5654	.inject_interrupt = kvmppc_inject_interrupt_hv,
5655	.set_msr     = kvmppc_set_msr_hv,
5656	.vcpu_run    = kvmppc_vcpu_run_hv,
5657	.vcpu_create = kvmppc_core_vcpu_create_hv,
5658	.vcpu_free   = kvmppc_core_vcpu_free_hv,
5659	.check_requests = kvmppc_core_check_requests_hv,
5660	.get_dirty_log  = kvm_vm_ioctl_get_dirty_log_hv,
5661	.flush_memslot  = kvmppc_core_flush_memslot_hv,
5662	.prepare_memory_region = kvmppc_core_prepare_memory_region_hv,
5663	.commit_memory_region  = kvmppc_core_commit_memory_region_hv,
5664	.unmap_hva_range = kvm_unmap_hva_range_hv,
5665	.age_hva  = kvm_age_hva_hv,
5666	.test_age_hva = kvm_test_age_hva_hv,
5667	.set_spte_hva = kvm_set_spte_hva_hv,
5668	.free_memslot = kvmppc_core_free_memslot_hv,
5669	.init_vm =  kvmppc_core_init_vm_hv,
5670	.destroy_vm = kvmppc_core_destroy_vm_hv,
5671	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv,
5672	.emulate_op = kvmppc_core_emulate_op_hv,
5673	.emulate_mtspr = kvmppc_core_emulate_mtspr_hv,
5674	.emulate_mfspr = kvmppc_core_emulate_mfspr_hv,
5675	.fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv,
5676	.arch_vm_ioctl  = kvm_arch_vm_ioctl_hv,
5677	.hcall_implemented = kvmppc_hcall_impl_hv,
5678#ifdef CONFIG_KVM_XICS
5679	.irq_bypass_add_producer = kvmppc_irq_bypass_add_producer_hv,
5680	.irq_bypass_del_producer = kvmppc_irq_bypass_del_producer_hv,
5681#endif
5682	.configure_mmu = kvmhv_configure_mmu,
5683	.get_rmmu_info = kvmhv_get_rmmu_info,
5684	.set_smt_mode = kvmhv_set_smt_mode,
5685	.enable_nested = kvmhv_enable_nested,
5686	.load_from_eaddr = kvmhv_load_from_eaddr,
5687	.store_to_eaddr = kvmhv_store_to_eaddr,
5688	.enable_svm = kvmhv_enable_svm,
5689	.svm_off = kvmhv_svm_off,
5690};
5691
5692static int kvm_init_subcore_bitmap(void)
5693{
5694	int i, j;
5695	int nr_cores = cpu_nr_cores();
5696	struct sibling_subcore_state *sibling_subcore_state;
5697
5698	for (i = 0; i < nr_cores; i++) {
5699		int first_cpu = i * threads_per_core;
5700		int node = cpu_to_node(first_cpu);
5701
5702		/* Ignore if it is already allocated. */
5703		if (paca_ptrs[first_cpu]->sibling_subcore_state)
5704			continue;
5705
5706		sibling_subcore_state =
5707			kzalloc_node(sizeof(struct sibling_subcore_state),
5708							GFP_KERNEL, node);
5709		if (!sibling_subcore_state)
5710			return -ENOMEM;
5711
5712
5713		for (j = 0; j < threads_per_core; j++) {
5714			int cpu = first_cpu + j;
5715
5716			paca_ptrs[cpu]->sibling_subcore_state =
5717						sibling_subcore_state;
5718		}
5719	}
5720	return 0;
5721}
5722
5723static int kvmppc_radix_possible(void)
5724{
5725	return cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled();
5726}
5727
5728static int kvmppc_book3s_init_hv(void)
5729{
5730	int r;
5731
5732	if (!tlbie_capable) {
5733		pr_err("KVM-HV: Host does not support TLBIE\n");
5734		return -ENODEV;
5735	}
5736
5737	/*
5738	 * FIXME!! Do we need to check on all cpus ?
5739	 */
5740	r = kvmppc_core_check_processor_compat_hv();
5741	if (r < 0)
5742		return -ENODEV;
5743
5744	r = kvmhv_nested_init();
5745	if (r)
5746		return r;
5747
5748	r = kvm_init_subcore_bitmap();
5749	if (r)
5750		return r;
5751
5752	/*
5753	 * We need a way of accessing the XICS interrupt controller,
5754	 * either directly, via paca_ptrs[cpu]->kvm_hstate.xics_phys, or
5755	 * indirectly, via OPAL.
5756	 */
5757#ifdef CONFIG_SMP
5758	if (!xics_on_xive() && !kvmhv_on_pseries() &&
5759	    !local_paca->kvm_hstate.xics_phys) {
5760		struct device_node *np;
5761
5762		np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
5763		if (!np) {
5764			pr_err("KVM-HV: Cannot determine method for accessing XICS\n");
5765			return -ENODEV;
5766		}
5767		/* presence of intc confirmed - node can be dropped again */
5768		of_node_put(np);
5769	}
5770#endif
5771
5772	kvm_ops_hv.owner = THIS_MODULE;
5773	kvmppc_hv_ops = &kvm_ops_hv;
5774
5775	init_default_hcalls();
5776
5777	init_vcore_lists();
5778
5779	r = kvmppc_mmu_hv_init();
5780	if (r)
5781		return r;
5782
5783	if (kvmppc_radix_possible()) {
5784		r = kvmppc_radix_init();
5785		if (r)
5786			return r;
5787	}
5788
5789	/*
5790	 * POWER9 chips before version 2.02 can't have some threads in
5791	 * HPT mode and some in radix mode on the same core.
5792	 */
5793	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
5794		unsigned int pvr = mfspr(SPRN_PVR);
5795		if ((pvr >> 16) == PVR_POWER9 &&
5796		    (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
5797		     ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
5798			no_mixing_hpt_and_radix = true;
5799	}
5800
5801	r = kvmppc_uvmem_init();
5802	if (r < 0)
5803		pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r);
5804
5805	return r;
5806}
5807
5808static void kvmppc_book3s_exit_hv(void)
5809{
5810	kvmppc_uvmem_free();
5811	kvmppc_free_host_rm_ops();
5812	if (kvmppc_radix_possible())
5813		kvmppc_radix_exit();
5814	kvmppc_hv_ops = NULL;
5815	kvmhv_nested_exit();
5816}
5817
5818module_init(kvmppc_book3s_init_hv);
5819module_exit(kvmppc_book3s_exit_hv);
5820MODULE_LICENSE("GPL");
5821MODULE_ALIAS_MISCDEV(KVM_MINOR);
5822MODULE_ALIAS("devname:kvm");
5823