summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_hv_builtin.c
blob: da85f046377a4bbb1534ec884cf42cc13b99d466 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 */

#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <linux/preempt.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/sizes.h>
#include <linux/cma.h>
#include <linux/bitops.h>

#include <asm/cputable.h>
#include <asm/interrupt.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/machdep.h>
#include <asm/xics.h>
#include <asm/xive.h>
#include <asm/dbell.h>
#include <asm/cputhreads.h>
#include <asm/io.h>
#include <asm/opal.h>
#include <asm/smp.h>

#define KVM_CMA_CHUNK_ORDER	18

#include "book3s_xics.h"
#include "book3s_xive.h"

/*
 * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
 * should be power of 2.
 */
#define HPT_ALIGN_PAGES		((1 << 18) >> PAGE_SHIFT) /* 256k */
/*
 * By default we reserve 5% of memory for hash pagetable allocation.
 */
static unsigned long kvm_cma_resv_ratio = 5;

static struct cma *kvm_cma;

static int __init early_parse_kvm_cma_resv(char *p)
{
	pr_debug("%s(%s)\n", __func__, p);
	if (!p)
		return -EINVAL;
	return kstrtoul(p, 0, &kvm_cma_resv_ratio);
}
early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv);

struct page *kvm_alloc_hpt_cma(unsigned long nr_pages)
{
	VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);

	return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES),
			 false);
}
EXPORT_SYMBOL_GPL(kvm_alloc_hpt_cma);

void kvm_free_hpt_cma(struct page *page, unsigned long nr_pages)
{
	cma_release(kvm_cma, page, nr_pages);
}
EXPORT_SYMBOL_GPL(kvm_free_hpt_cma);

/**
 * kvm_cma_reserve() - reserve area for kvm hash pagetable
 *
 * This function reserves memory from early allocator. It should be
 * called by arch specific code once the memblock allocator
 * has been activated and all other subsystems have already allocated/reserved
 * memory.
 */
void __init kvm_cma_reserve(void)
{
	unsigned long align_size;
	phys_addr_t selected_size;

	/*
	 * We need CMA reservation only when we are in HV mode
	 */
	if (!cpu_has_feature(CPU_FTR_HVMODE))
		return;

	selected_size = PAGE_ALIGN(memblock_phys_mem_size() * kvm_cma_resv_ratio / 100);
	if (selected_size) {
		pr_info("%s: reserving %ld MiB for global area\n", __func__,
			 (unsigned long)selected_size / SZ_1M);
		align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
		cma_declare_contiguous(0, selected_size, 0, align_size,
			KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, "kvm_cma",
			&kvm_cma);
	}
}

/*
 * Real-mode H_CONFER implementation.
 * We check if we are the only vcpu out of this virtual core
 * still running in the guest and not ceded.  If so, we pop up
 * to the virtual-mode implementation; if not, just return to
 * the guest.
 */
long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
			    unsigned int yield_count)
{
	struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
	int ptid = local_paca->kvm_hstate.ptid;
	int threads_running;
	int threads_ceded;
	int threads_conferring;
	u64 stop = get_tb() + 10 * tb_ticks_per_usec;
	int rv = H_SUCCESS; /* => don't yield */

	set_bit(ptid, &vc->conferring_threads);
	while ((get_tb() < stop) && !VCORE_IS_EXITING(vc)) {
		threads_running = VCORE_ENTRY_MAP(vc);
		threads_ceded = vc->napping_threads;
		threads_conferring = vc->conferring_threads;
		if ((threads_ceded | threads_conferring) == threads_running) {
			rv = H_TOO_HARD; /* => do yield */
			break;
		}
	}
	clear_bit(ptid, &vc->conferring_threads);
	return rv;
}

/*
 * When running HV mode KVM we need to block certain operations while KVM VMs
 * exist in the system. We use a counter of VMs to track this.
 *
 * One of the operations we need to block is onlining of secondaries, so we
 * protect hv_vm_count with cpus_read_lock/unlock().
 */
static atomic_t hv_vm_count;

void kvm_hv_vm_activated(void)
{
	cpus_read_lock();
	atomic_inc(&hv_vm_count);
	cpus_read_unlock();
}
EXPORT_SYMBOL_GPL(kvm_hv_vm_activated);

void kvm_hv_vm_deactivated(void)
{
	cpus_read_lock();
	atomic_dec(&hv_vm_count);
	cpus_read_unlock();
}
EXPORT_SYMBOL_GPL(kvm_hv_vm_deactivated);

bool kvm_hv_mode_active(void)
{
	return atomic_read(&hv_vm_count) != 0;
}

extern int hcall_real_table[], hcall_real_table_end[];

int kvmppc_hcall_impl_hv_realmode(unsigned long cmd)
{
	cmd /= 4;
	if (cmd < hcall_real_table_end - hcall_real_table &&
	    hcall_real_table[cmd])
		return 1;

	return 0;
}
EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode);

int kvmppc_hwrng_present(void)
{
	return ppc_md.get_random_seed != NULL;
}
EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);

long kvmppc_rm_h_random(struct kvm_vcpu *vcpu)
{
	if (ppc_md.get_random_seed &&
	    ppc_md.get_random_seed(&vcpu->arch.regs.gpr[4]))
		return H_SUCCESS;

	return H_HARDWARE;
}

/*
 * Send an interrupt or message to another CPU.
 * The caller needs to include any barrier needed to order writes
 * to memory vs. the IPI/message.
 */
void kvmhv_rm_send_ipi(int cpu)
{
	void __iomem *xics_phys;
	unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);

	/* On POWER9 we can use msgsnd for any destination cpu. */
	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
		msg |= get_hard_smp_processor_id(cpu);
		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
		return;
	}

	/* On POWER8 for IPIs to threads in the same core, use msgsnd. */
	if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
	    cpu_first_thread_sibling(cpu) ==
	    cpu_first_thread_sibling(raw_smp_processor_id())) {
		msg |= cpu_thread_in_core(cpu);
		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
		return;
	}

	/* We should never reach this */
	if (WARN_ON_ONCE(xics_on_xive()))
	    return;

	/* Else poke the target with an IPI */
	xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys;
	if (xics_phys)
		__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
	else
		opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY);
}

/*
 * The following functions are called from the assembly code
 * in book3s_hv_rmhandlers.S.
 */
static void kvmhv_interrupt_vcore(struct kvmppc_vcore *vc, int active)
{
	int cpu = vc->pcpu;

	/* Order setting of exit map vs. msgsnd/IPI */
	smp_mb();
	for (; active; active >>= 1, ++cpu)
		if (active & 1)
			kvmhv_rm_send_ipi(cpu);
}

void kvmhv_commence_exit(int trap)
{
	struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
	int ptid = local_paca->kvm_hstate.ptid;
	struct kvm_split_mode *sip = local_paca->kvm_hstate.kvm_split_mode;
	int me, ee, i;

	/* Set our bit in the threads-exiting-guest map in the 0xff00
	   bits of vcore->entry_exit_map */
	me = 0x100 << ptid;
	do {
		ee = vc->entry_exit_map;
	} while (cmpxchg(&vc->entry_exit_map, ee, ee | me) != ee);

	/* Are we the first here? */
	if ((ee >> 8) != 0)
		return;

	/*
	 * Trigger the other threads in this vcore to exit the guest.
	 * If this is a hypervisor decrementer interrupt then they
	 * will be already on their way out of the guest.
	 */
	if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
		kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));

	/*
	 * If we are doing dynamic micro-threading, interrupt the other
	 * subcores to pull them out of their guests too.
	 */
	if (!sip)
		return;

	for (i = 0; i < MAX_SUBCORES; ++i) {
		vc = sip->vc[i];
		if (!vc)
			break;
		do {
			ee = vc->entry_exit_map;
			/* Already asked to exit? */
			if ((ee >> 8) != 0)
				break;
		} while (cmpxchg(&vc->entry_exit_map, ee,
				 ee | VCORE_EXIT_REQ) != ee);
		if ((ee >> 8) == 0)
			kvmhv_interrupt_vcore(vc, ee);
	}
}

struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv;
EXPORT_SYMBOL_GPL(kvmppc_host_rm_ops_hv);

#ifdef CONFIG_KVM_XICS
static struct kvmppc_irq_map *get_irqmap(struct kvmppc_passthru_irqmap *pimap,
					 u32 xisr)
{
	int i;

	/*
	 * We access the mapped array here without a lock.  That
	 * is safe because we never reduce the number of entries
	 * in the array and we never change the v_hwirq field of
	 * an entry once it is set.
	 *
	 * We have also carefully ordered the stores in the writer
	 * and the loads here in the reader, so that if we find a matching
	 * hwirq here, the associated GSI and irq_desc fields are valid.
	 */
	for (i = 0; i < pimap->n_mapped; i++)  {
		if (xisr == pimap->mapped[i].r_hwirq) {
			/*
			 * Order subsequent reads in the caller to serialize
			 * with the writer.
			 */
			smp_rmb();
			return &pimap->mapped[i];
		}
	}
	return NULL;
}

/*
 * If we have an interrupt that's not an IPI, check if we have a
 * passthrough adapter and if so, check if this external interrupt
 * is for the adapter.
 * We will attempt to deliver the IRQ directly to the target VCPU's
 * ICP, the virtual ICP (based on affinity - the xive value in ICS).
 *
 * If the delivery fails or if this is not for a passthrough adapter,
 * return to the host to handle this interrupt. We earlier
 * saved a copy of the XIRR in the PACA, it will be picked up by
 * the host ICP driver.
 */
static int kvmppc_check_passthru(u32 xisr, __be32 xirr, bool *again)
{
	struct kvmppc_passthru_irqmap *pimap;
	struct kvmppc_irq_map *irq_map;
	struct kvm_vcpu *vcpu;

	vcpu = local_paca->kvm_hstate.kvm_vcpu;
	if (!vcpu)
		return 1;
	pimap = kvmppc_get_passthru_irqmap(vcpu->kvm);
	if (!pimap)
		return 1;
	irq_map = get_irqmap(pimap, xisr);
	if (!irq_map)
		return 1;

	/* We're handling this interrupt, generic code doesn't need to */
	local_paca->kvm_hstate.saved_xirr = 0;

	return kvmppc_deliver_irq_passthru(vcpu, xirr, irq_map, pimap, again);
}

#else
static inline int kvmppc_check_passthru(u32 xisr, __be32 xirr, bool *again)
{
	return 1;
}
#endif

/*
 * Determine what sort of external interrupt is pending (if any).
 * Returns:
 *	0 if no interrupt is pending
 *	1 if an interrupt is pending that needs to be handled by the host
 *	2 Passthrough that needs completion in the host
 *	-1 if there was a guest wakeup IPI (which has now been cleared)
 *	-2 if there is PCI passthrough external interrupt that was handled
 */
static long kvmppc_read_one_intr(bool *again);

long kvmppc_read_intr(void)
{
	long ret = 0;
	long rc;
	bool again;

	if (xive_enabled())
		return 1;

	do {
		again = false;
		rc = kvmppc_read_one_intr(&again);
		if (rc && (ret == 0 || rc > ret))
			ret = rc;
	} while (again);
	return ret;
}

static long kvmppc_read_one_intr(bool *again)
{
	void __iomem *xics_phys;
	u32 h_xirr;
	__be32 xirr;
	u32 xisr;
	u8 host_ipi;
	int64_t rc;

	if (xive_enabled())
		return 1;

	/* see if a host IPI is pending */
	host_ipi = local_paca->kvm_hstate.host_ipi;
	if (host_ipi)
		return 1;

	/* Now read the interrupt from the ICP */
	xics_phys = local_paca->kvm_hstate.xics_phys;
	rc = 0;
	if (!xics_phys)
		rc = opal_int_get_xirr(&xirr, false);
	else
		xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
	if (rc < 0)
		return 1;

	/*
	 * Save XIRR for later. Since we get control in reverse endian
	 * on LE systems, save it byte reversed and fetch it back in
	 * host endian. Note that xirr is the value read from the
	 * XIRR register, while h_xirr is the host endian version.
	 */
	h_xirr = be32_to_cpu(xirr);
	local_paca->kvm_hstate.saved_xirr = h_xirr;
	xisr = h_xirr & 0xffffff;
	/*
	 * Ensure that the store/load complete to guarantee all side
	 * effects of loading from XIRR has completed
	 */
	smp_mb();

	/* if nothing pending in the ICP */
	if (!xisr)
		return 0;

	/* We found something in the ICP...
	 *
	 * If it is an IPI, clear the MFRR and EOI it.
	 */
	if (xisr == XICS_IPI) {
		rc = 0;
		if (xics_phys) {
			__raw_rm_writeb(0xff, xics_phys + XICS_MFRR);
			__raw_rm_writel(xirr, xics_phys + XICS_XIRR);
		} else {
			opal_int_set_mfrr(hard_smp_processor_id(), 0xff);
			rc = opal_int_eoi(h_xirr);
		}
		/* If rc > 0, there is another interrupt pending */
		*again = rc > 0;

		/*
		 * Need to ensure side effects of above stores
		 * complete before proceeding.
		 */
		smp_mb();

		/*
		 * We need to re-check host IPI now in case it got set in the
		 * meantime. If it's clear, we bounce the interrupt to the
		 * guest
		 */
		host_ipi = local_paca->kvm_hstate.host_ipi;
		if (unlikely(host_ipi != 0)) {
			/* We raced with the host,
			 * we need to resend that IPI, bummer
			 */
			if (xics_phys)
				__raw_rm_writeb(IPI_PRIORITY,
						xics_phys + XICS_MFRR);
			else
				opal_int_set_mfrr(hard_smp_processor_id(),
						  IPI_PRIORITY);
			/* Let side effects complete */
			smp_mb();
			return 1;
		}

		/* OK, it's an IPI for us */
		local_paca->kvm_hstate.saved_xirr = 0;
		return -1;
	}

	return kvmppc_check_passthru(xisr, xirr, again);
}

static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
{
	vcpu->arch.ceded = 0;
	if (vcpu->arch.timer_running) {
		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
		vcpu->arch.timer_running = 0;
	}
}

void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
{
	/* Guest must always run with ME enabled, HV disabled. */
	msr = (msr | MSR_ME) & ~MSR_HV;

	/*
	 * Check for illegal transactional state bit combination
	 * and if we find it, force the TS field to a safe state.
	 */
	if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
		msr &= ~MSR_TS_MASK;
	vcpu->arch.shregs.msr = msr;
	kvmppc_end_cede(vcpu);
}
EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv);

static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
{
	unsigned long msr, pc, new_msr, new_pc;

	msr = kvmppc_get_msr(vcpu);
	pc = kvmppc_get_pc(vcpu);
	new_msr = vcpu->arch.intr_msr;
	new_pc = vec;

	/* If transactional, change to suspend mode on IRQ delivery */
	if (MSR_TM_TRANSACTIONAL(msr))
		new_msr |= MSR_TS_S;
	else
		new_msr |= msr & MSR_TS_MASK;

	/*
	 * Perform MSR and PC adjustment for LPCR[AIL]=3 if it is set and
	 * applicable. AIL=2 is not supported.
	 *
	 * AIL does not apply to SRESET, MCE, or HMI (which is never
	 * delivered to the guest), and does not apply if IR=0 or DR=0.
	 */
	if (vec != BOOK3S_INTERRUPT_SYSTEM_RESET &&
	    vec != BOOK3S_INTERRUPT_MACHINE_CHECK &&
	    (vcpu->arch.vcore->lpcr & LPCR_AIL) == LPCR_AIL_3 &&
	    (msr & (MSR_IR|MSR_DR)) == (MSR_IR|MSR_DR) ) {
		new_msr |= MSR_IR | MSR_DR;
		new_pc += 0xC000000000004000ULL;
	}

	kvmppc_set_srr0(vcpu, pc);
	kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags);
	kvmppc_set_pc(vcpu, new_pc);
	vcpu->arch.shregs.msr = new_msr;
}

void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
{
	inject_interrupt(vcpu, vec, srr1_flags);
	kvmppc_end_cede(vcpu);
}
EXPORT_SYMBOL_GPL(kvmppc_inject_interrupt_hv);

/*
 * Is there a PRIV_DOORBELL pending for the guest (on POWER9)?
 * Can we inject a Decrementer or a External interrupt?
 */
void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
{
	int ext;
	unsigned long lpcr;

	WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300));

	/* Insert EXTERNAL bit into LPCR at the MER bit position */
	ext = (vcpu->arch.pending_exceptions >> BOOK3S_IRQPRIO_EXTERNAL) & 1;
	lpcr = mfspr(SPRN_LPCR);
	lpcr |= ext << LPCR_MER_SH;
	mtspr(SPRN_LPCR, lpcr);
	isync();

	if (vcpu->arch.shregs.msr & MSR_EE) {
		if (ext) {
			inject_interrupt(vcpu, BOOK3S_INTERRUPT_EXTERNAL, 0);
		} else {
			long int dec = mfspr(SPRN_DEC);
			if (!(lpcr & LPCR_LD))
				dec = (int) dec;
			if (dec < 0)
				inject_interrupt(vcpu,
					BOOK3S_INTERRUPT_DECREMENTER, 0);
		}
	}

	if (vcpu->arch.doorbell_request) {
		mtspr(SPRN_DPDES, 1);
		vcpu->arch.vcore->dpdes = 1;
		smp_wmb();
		vcpu->arch.doorbell_request = 0;
	}
}

static void flush_guest_tlb(struct kvm *kvm)
{
	unsigned long rb, set;

	rb = PPC_BIT(52);	/* IS = 2 */
	for (set = 0; set < kvm->arch.tlb_sets; ++set) {
		/* R=0 PRS=0 RIC=0 */
		asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
			     : : "r" (rb), "i" (0), "i" (0), "i" (0),
			       "r" (0) : "memory");
		rb += PPC_BIT(51);	/* increment set number */
	}
	asm volatile("ptesync": : :"memory");
}

void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu)
{
	if (cpumask_test_cpu(pcpu, &kvm->arch.need_tlb_flush)) {
		flush_guest_tlb(kvm);

		/* Clear the bit after the TLB flush */
		cpumask_clear_cpu(pcpu, &kvm->arch.need_tlb_flush);
	}
}
EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush);