summaryrefslogtreecommitdiffstats
path: root/sys/x86/xen/hvm.c
blob: 2286cf00ca6c1e126c33baca845c83d5c512d496 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
/*
 * Copyright (c) 2008, 2013 Citrix Systems, Inc.
 * Copyright (c) 2012 Spectra Logic Corporation
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include <sys/param.h>
#include <sys/bus.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/proc.h>
#include <sys/smp.h>
#include <sys/systm.h>

#include <vm/vm.h>
#include <vm/pmap.h>

#include <dev/pci/pcivar.h>

#include <machine/cpufunc.h>
#include <machine/cpu.h>
#include <machine/smp.h>

#include <x86/apicreg.h>

#include <xen/xen-os.h>
#include <xen/features.h>
#include <xen/gnttab.h>
#include <xen/hypervisor.h>
#include <xen/hvm.h>
#include <xen/xen_intr.h>

#include <xen/interface/hvm/params.h>
#include <xen/interface/vcpu.h>

/*--------------------------- Forward Declarations ---------------------------*/
#ifdef SMP
static driver_filter_t xen_smp_rendezvous_action;
static driver_filter_t xen_invltlb;
static driver_filter_t xen_invlpg;
static driver_filter_t xen_invlrng;
static driver_filter_t xen_invlcache;
#ifdef __i386__
static driver_filter_t xen_lazypmap;
#endif
static driver_filter_t xen_ipi_bitmap_handler;
static driver_filter_t xen_cpustop_handler;
static driver_filter_t xen_cpususpend_handler;
static driver_filter_t xen_cpustophard_handler;
#endif
static void xen_ipi_vectored(u_int vector, int dest);
static void xen_hvm_cpu_resume(void);
static void xen_hvm_cpu_init(void);

/*---------------------------- Extern Declarations ---------------------------*/
/* Variables used by mp_machdep to perform the MMU related IPIs */
extern volatile int smp_tlb_wait;
extern vm_offset_t smp_tlb_addr2;
#ifdef __i386__
extern vm_offset_t smp_tlb_addr1;
#else
extern struct invpcid_descr smp_tlb_invpcid;
extern uint64_t pcid_cr3;
extern int invpcid_works;
extern int pmap_pcid_enabled;
extern pmap_t smp_tlb_pmap;
#endif

#ifdef __i386__
extern void pmap_lazyfix_action(void);
#endif

/* Variables used by mp_machdep to perform the bitmap IPI */
extern volatile u_int cpu_ipi_pending[MAXCPU];

/*---------------------------------- Macros ----------------------------------*/
#define	IPI_TO_IDX(ipi) ((ipi) - APIC_IPI_INTS)

/*-------------------------------- Local Types -------------------------------*/
enum xen_hvm_init_type {
	XEN_HVM_INIT_COLD,
	XEN_HVM_INIT_CANCELLED_SUSPEND,
	XEN_HVM_INIT_RESUME
};

struct xen_ipi_handler
{
	driver_filter_t	*filter;
	const char	*description;
};

/*-------------------------------- Global Data -------------------------------*/
enum xen_domain_type xen_domain_type = XEN_NATIVE;

struct cpu_ops xen_hvm_cpu_ops = {
	.ipi_vectored	= xen_ipi_vectored,
	.cpu_init	= xen_hvm_cpu_init,
	.cpu_resume	= xen_hvm_cpu_resume
};

static MALLOC_DEFINE(M_XENHVM, "xen_hvm", "Xen HVM PV Support");

#ifdef SMP
static struct xen_ipi_handler xen_ipis[] = 
{
	[IPI_TO_IDX(IPI_RENDEZVOUS)]	= { xen_smp_rendezvous_action,	"r"   },
	[IPI_TO_IDX(IPI_INVLTLB)]	= { xen_invltlb,		"itlb"},
	[IPI_TO_IDX(IPI_INVLPG)]	= { xen_invlpg,			"ipg" },
	[IPI_TO_IDX(IPI_INVLRNG)]	= { xen_invlrng,		"irg" },
	[IPI_TO_IDX(IPI_INVLCACHE)]	= { xen_invlcache,		"ic"  },
#ifdef __i386__
	[IPI_TO_IDX(IPI_LAZYPMAP)]	= { xen_lazypmap,		"lp"  },
#endif
	[IPI_TO_IDX(IPI_BITMAP_VECTOR)] = { xen_ipi_bitmap_handler,	"b"   },
	[IPI_TO_IDX(IPI_STOP)]		= { xen_cpustop_handler,	"st"  },
	[IPI_TO_IDX(IPI_SUSPEND)]	= { xen_cpususpend_handler,	"sp"  },
	[IPI_TO_IDX(IPI_STOP_HARD)]	= { xen_cpustophard_handler,	"sth" },
};
#endif

/**
 * If non-zero, the hypervisor has been configured to use a direct
 * IDT event callback for interrupt injection.
 */
int xen_vector_callback_enabled;

/*------------------------------- Per-CPU Data -------------------------------*/
DPCPU_DEFINE(struct vcpu_info, vcpu_local_info);
DPCPU_DEFINE(struct vcpu_info *, vcpu_info);
#ifdef SMP
DPCPU_DEFINE(xen_intr_handle_t, ipi_handle[nitems(xen_ipis)]);
#endif

/*------------------ Hypervisor Access Shared Memory Regions -----------------*/
/** Hypercall table accessed via HYPERVISOR_*_op() methods. */
char *hypercall_stubs;
shared_info_t *HYPERVISOR_shared_info;

#ifdef SMP
/*---------------------------- XEN PV IPI Handlers ---------------------------*/
/*
 * This are C clones of the ASM functions found in apic_vector.s
 */
static int
xen_ipi_bitmap_handler(void *arg)
{
	struct trapframe *frame;

	frame = arg;
	ipi_bitmap_handler(*frame);
	return (FILTER_HANDLED);
}

static int
xen_smp_rendezvous_action(void *arg)
{
#ifdef COUNT_IPIS
	int cpu;

	cpu = PCPU_GET(cpuid);
	(*ipi_rendezvous_counts[cpu])++;
#endif /* COUNT_IPIS */

	smp_rendezvous_action();
	return (FILTER_HANDLED);
}

static int
xen_invltlb(void *arg)
{
#if defined(COUNT_XINVLTLB_HITS) || defined(COUNT_IPIS)
	int cpu;

	cpu = PCPU_GET(cpuid);
#ifdef COUNT_XINVLTLB_HITS
	xhits_gbl[cpu]++;
#endif /* COUNT_XINVLTLB_HITS */
#ifdef COUNT_IPIS
	(*ipi_invltlb_counts[cpu])++;
#endif /* COUNT_IPIS */
#endif /* COUNT_XINVLTLB_HITS || COUNT_IPIS */

	invltlb();
	atomic_add_int(&smp_tlb_wait, 1);
	return (FILTER_HANDLED);
}

#ifdef __amd64__
static int
xen_invltlb_pcid(void *arg)
{
	uint64_t cr3;
#if defined(COUNT_XINVLTLB_HITS) || defined(COUNT_IPIS)
	int cpu;

	cpu = PCPU_GET(cpuid);
#ifdef COUNT_XINVLTLB_HITS
	xhits_gbl[cpu]++;
#endif /* COUNT_XINVLTLB_HITS */
#ifdef COUNT_IPIS
	(*ipi_invltlb_counts[cpu])++;
#endif /* COUNT_IPIS */
#endif /* COUNT_XINVLTLB_HITS || COUNT_IPIS */

	cr3 = rcr3();
	if (smp_tlb_invpcid.pcid != (uint64_t)-1 &&
	    smp_tlb_invpcid.pcid != 0) {

		if (invpcid_works) {
			invpcid(&smp_tlb_invpcid, INVPCID_CTX);
		} else {
			/* Otherwise reload %cr3 twice. */
			if (cr3 != pcid_cr3) {
				load_cr3(pcid_cr3);
				cr3 |= CR3_PCID_SAVE;
			}
			load_cr3(cr3);
		}
	} else {
		invltlb_globpcid();
	}
	if (smp_tlb_pmap != NULL)
		CPU_CLR_ATOMIC(PCPU_GET(cpuid), &smp_tlb_pmap->pm_save);

	atomic_add_int(&smp_tlb_wait, 1);
	return (FILTER_HANDLED);
}
#endif

static int
xen_invlpg(void *arg)
{
#if defined(COUNT_XINVLTLB_HITS) || defined(COUNT_IPIS)
	int cpu;

	cpu = PCPU_GET(cpuid);
#ifdef COUNT_XINVLTLB_HITS
	xhits_pg[cpu]++;
#endif /* COUNT_XINVLTLB_HITS */
#ifdef COUNT_IPIS
	(*ipi_invlpg_counts[cpu])++;
#endif /* COUNT_IPIS */
#endif /* COUNT_XINVLTLB_HITS || COUNT_IPIS */

#ifdef __i386__
	invlpg(smp_tlb_addr1);
#else
	invlpg(smp_tlb_invpcid.addr);
#endif
	atomic_add_int(&smp_tlb_wait, 1);
	return (FILTER_HANDLED);
}

#ifdef __amd64__
static int
xen_invlpg_pcid(void *arg)
{
#if defined(COUNT_XINVLTLB_HITS) || defined(COUNT_IPIS)
	int cpu;

	cpu = PCPU_GET(cpuid);
#ifdef COUNT_XINVLTLB_HITS
	xhits_pg[cpu]++;
#endif /* COUNT_XINVLTLB_HITS */
#ifdef COUNT_IPIS
	(*ipi_invlpg_counts[cpu])++;
#endif /* COUNT_IPIS */
#endif /* COUNT_XINVLTLB_HITS || COUNT_IPIS */

	if (invpcid_works) {
		invpcid(&smp_tlb_invpcid, INVPCID_ADDR);
	} else if (smp_tlb_invpcid.pcid == 0) {
		invlpg(smp_tlb_invpcid.addr);
	} else if (smp_tlb_invpcid.pcid == (uint64_t)-1) {
		invltlb_globpcid();
	} else {
		uint64_t cr3;

		/*
		 * PCID supported, but INVPCID is not.
		 * Temporarily switch to the target address
		 * space and do INVLPG.
		 */
		cr3 = rcr3();
		if (cr3 != pcid_cr3)
			load_cr3(pcid_cr3 | CR3_PCID_SAVE);
		invlpg(smp_tlb_invpcid.addr);
		load_cr3(cr3 | CR3_PCID_SAVE);
	}

	atomic_add_int(&smp_tlb_wait, 1);
	return (FILTER_HANDLED);
}
#endif

static inline void
invlpg_range(vm_offset_t start, vm_offset_t end)
{
	do {
		invlpg(start);
		start += PAGE_SIZE;
	} while (start < end);
}

static int
xen_invlrng(void *arg)
{
	vm_offset_t addr;
#if defined(COUNT_XINVLTLB_HITS) || defined(COUNT_IPIS)
	int cpu;

	cpu = PCPU_GET(cpuid);
#ifdef COUNT_XINVLTLB_HITS
	xhits_rng[cpu]++;
#endif /* COUNT_XINVLTLB_HITS */
#ifdef COUNT_IPIS
	(*ipi_invlrng_counts[cpu])++;
#endif /* COUNT_IPIS */
#endif /* COUNT_XINVLTLB_HITS || COUNT_IPIS */

#ifdef __i386__
	addr = smp_tlb_addr1;
	invlpg_range(addr, smp_tlb_addr2);
#else
	addr = smp_tlb_invpcid.addr;
	if (pmap_pcid_enabled) {
		if (invpcid_works) {
			struct invpcid_descr d;

			d = smp_tlb_invpcid;
			do {
				invpcid(&d, INVPCID_ADDR);
				d.addr += PAGE_SIZE;
			} while (d.addr < smp_tlb_addr2);
		} else if (smp_tlb_invpcid.pcid == 0) {
			/*
			 * kernel pmap - use invlpg to invalidate
			 * global mapping.
			 */
			invlpg_range(addr, smp_tlb_addr2);
		} else if (smp_tlb_invpcid.pcid != (uint64_t)-1) {
			invltlb_globpcid();
			if (smp_tlb_pmap != NULL) {
				CPU_CLR_ATOMIC(PCPU_GET(cpuid),
				    &smp_tlb_pmap->pm_save);
			}
		} else {
			uint64_t cr3;

			cr3 = rcr3();
			if (cr3 != pcid_cr3)
				load_cr3(pcid_cr3 | CR3_PCID_SAVE);
			invlpg_range(addr, smp_tlb_addr2);
			load_cr3(cr3 | CR3_PCID_SAVE);
		}
	} else {
		invlpg_range(addr, smp_tlb_addr2);
	}
#endif

	atomic_add_int(&smp_tlb_wait, 1);
	return (FILTER_HANDLED);
}

static int
xen_invlcache(void *arg)
{
#ifdef COUNT_IPIS
	int cpu = PCPU_GET(cpuid);

	cpu = PCPU_GET(cpuid);
	(*ipi_invlcache_counts[cpu])++;
#endif /* COUNT_IPIS */

	wbinvd();
	atomic_add_int(&smp_tlb_wait, 1);
	return (FILTER_HANDLED);
}

#ifdef __i386__
static int
xen_lazypmap(void *arg)
{

	pmap_lazyfix_action();
	return (FILTER_HANDLED);
}
#endif

static int
xen_cpustop_handler(void *arg)
{

	cpustop_handler();
	return (FILTER_HANDLED);
}

static int
xen_cpususpend_handler(void *arg)
{

	cpususpend_handler();
	return (FILTER_HANDLED);
}

static int
xen_cpustophard_handler(void *arg)
{

	ipi_nmi_handler();
	return (FILTER_HANDLED);
}

/* Xen PV IPI sender */
static void
xen_ipi_vectored(u_int vector, int dest)
{
	xen_intr_handle_t *ipi_handle;
	int ipi_idx, to_cpu, self;

	ipi_idx = IPI_TO_IDX(vector);
	if (ipi_idx > nitems(xen_ipis))
		panic("IPI out of range");

	switch(dest) {
	case APIC_IPI_DEST_SELF:
		ipi_handle = DPCPU_GET(ipi_handle);
		xen_intr_signal(ipi_handle[ipi_idx]);
		break;
	case APIC_IPI_DEST_ALL:
		CPU_FOREACH(to_cpu) {
			ipi_handle = DPCPU_ID_GET(to_cpu, ipi_handle);
			xen_intr_signal(ipi_handle[ipi_idx]);
		}
		break;
	case APIC_IPI_DEST_OTHERS:
		self = PCPU_GET(cpuid);
		CPU_FOREACH(to_cpu) {
			if (to_cpu != self) {
				ipi_handle = DPCPU_ID_GET(to_cpu, ipi_handle);
				xen_intr_signal(ipi_handle[ipi_idx]);
			}
		}
		break;
	default:
		to_cpu = apic_cpuid(dest);
		ipi_handle = DPCPU_ID_GET(to_cpu, ipi_handle);
		xen_intr_signal(ipi_handle[ipi_idx]);
		break;
	}
}

/* XEN diverged cpu operations */
static void
xen_hvm_cpu_resume(void)
{
	u_int cpuid = PCPU_GET(cpuid);

	/*
	 * Reset pending bitmap IPIs, because Xen doesn't preserve pending
	 * event channels on migration.
	 */
	cpu_ipi_pending[cpuid] = 0;

	/* register vcpu_info area */
	xen_hvm_cpu_init();
}

static void
xen_cpu_ipi_init(int cpu)
{
	xen_intr_handle_t *ipi_handle;
	const struct xen_ipi_handler *ipi;
	device_t dev;
	int idx, rc;

	ipi_handle = DPCPU_ID_GET(cpu, ipi_handle);
	dev = pcpu_find(cpu)->pc_device;
	KASSERT((dev != NULL), ("NULL pcpu device_t"));

	for (ipi = xen_ipis, idx = 0; idx < nitems(xen_ipis); ipi++, idx++) {

		if (ipi->filter == NULL) {
			ipi_handle[idx] = NULL;
			continue;
		}

		rc = xen_intr_alloc_and_bind_ipi(dev, cpu, ipi->filter,
		    INTR_TYPE_TTY, &ipi_handle[idx]);
		if (rc != 0)
			panic("Unable to allocate a XEN IPI port");
		xen_intr_describe(ipi_handle[idx], "%s", ipi->description);
	}
}

static void
xen_setup_cpus(void)
{
	int i;

	if (!xen_hvm_domain() || !xen_vector_callback_enabled)
		return;

#ifdef __amd64__
	if (pmap_pcid_enabled) {
		xen_ipis[IPI_TO_IDX(IPI_INVLTLB)].filter = xen_invltlb_pcid;
		xen_ipis[IPI_TO_IDX(IPI_INVLPG)].filter = xen_invlpg_pcid;
	}
#endif
	CPU_FOREACH(i)
		xen_cpu_ipi_init(i);

	/* Set the xen pv ipi ops to replace the native ones */
	cpu_ops = xen_hvm_cpu_ops;
}
#endif

/*---------------------- XEN Hypervisor Probe and Setup ----------------------*/
static uint32_t
xen_hvm_cpuid_base(void)
{
	uint32_t base, regs[4];

	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
		do_cpuid(base, regs);
		if (!memcmp("XenVMMXenVMM", &regs[1], 12)
		    && (regs[0] - base) >= 2)
			return (base);
	}
	return (0);
}

/*
 * Allocate and fill in the hypcall page.
 */
static int
xen_hvm_init_hypercall_stubs(void)
{
	uint32_t base, regs[4];
	int i;

	base = xen_hvm_cpuid_base();
	if (base == 0)
		return (ENXIO);

	if (hypercall_stubs == NULL) {
		do_cpuid(base + 1, regs);
		printf("XEN: Hypervisor version %d.%d detected.\n",
		    regs[0] >> 16, regs[0] & 0xffff);
	}

	/*
	 * Find the hypercall pages.
	 */
	do_cpuid(base + 2, regs);
	
	if (hypercall_stubs == NULL) {
		size_t call_region_size;

		call_region_size = regs[0] * PAGE_SIZE;
		hypercall_stubs = malloc(call_region_size, M_XENHVM, M_NOWAIT);
		if (hypercall_stubs == NULL)
			panic("Unable to allocate Xen hypercall region");
	}

	for (i = 0; i < regs[0]; i++)
		wrmsr(regs[1], vtophys(hypercall_stubs + i * PAGE_SIZE) + i);

	return (0);
}

static void
xen_hvm_init_shared_info_page(void)
{
	struct xen_add_to_physmap xatp;

	if (HYPERVISOR_shared_info == NULL) {
		HYPERVISOR_shared_info = malloc(PAGE_SIZE, M_XENHVM, M_NOWAIT);
		if (HYPERVISOR_shared_info == NULL)
			panic("Unable to allocate Xen shared info page");
	}

	xatp.domid = DOMID_SELF;
	xatp.idx = 0;
	xatp.space = XENMAPSPACE_shared_info;
	xatp.gpfn = vtophys(HYPERVISOR_shared_info) >> PAGE_SHIFT;
	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
		panic("HYPERVISOR_memory_op failed");
}

/*
 * Tell the hypervisor how to contact us for event channel callbacks.
 */
void
xen_hvm_set_callback(device_t dev)
{
	struct xen_hvm_param xhp;
	int irq;

	if (xen_vector_callback_enabled)
		return;

	xhp.domid = DOMID_SELF;
	xhp.index = HVM_PARAM_CALLBACK_IRQ;
	if (xen_feature(XENFEAT_hvm_callback_vector) != 0) {
		int error;

		xhp.value = HVM_CALLBACK_VECTOR(IDT_EVTCHN);
		error = HYPERVISOR_hvm_op(HVMOP_set_param, &xhp);
		if (error == 0) {
			xen_vector_callback_enabled = 1;
			return;
		}
		printf("Xen HVM callback vector registration failed (%d). "
		    "Falling back to emulated device interrupt\n", error);
	}
	xen_vector_callback_enabled = 0;
	if (dev == NULL) {
		/*
		 * Called from early boot or resume.
		 * xenpci will invoke us again later.
		 */
		return;
	}

	irq = pci_get_irq(dev);
	if (irq < 16) {
		xhp.value = HVM_CALLBACK_GSI(irq);
	} else {
		u_int slot;
		u_int pin;

		slot = pci_get_slot(dev);
		pin = pci_get_intpin(dev) - 1;
		xhp.value = HVM_CALLBACK_PCI_INTX(slot, pin);
	}

	if (HYPERVISOR_hvm_op(HVMOP_set_param, &xhp) != 0)
		panic("Can't set evtchn callback");
}

#define	XEN_MAGIC_IOPORT 0x10
enum {
	XMI_MAGIC			 = 0x49d2,
	XMI_UNPLUG_IDE_DISKS		 = 0x01,
	XMI_UNPLUG_NICS			 = 0x02,
	XMI_UNPLUG_IDE_EXCEPT_PRI_MASTER = 0x04
};

static void
xen_hvm_disable_emulated_devices(void)
{
	if (inw(XEN_MAGIC_IOPORT) != XMI_MAGIC)
		return;

	if (bootverbose)
		printf("XEN: Disabling emulated block and network devices\n");
	outw(XEN_MAGIC_IOPORT, XMI_UNPLUG_IDE_DISKS|XMI_UNPLUG_NICS);
}

static void
xen_hvm_init(enum xen_hvm_init_type init_type)
{
	int error;
	int i;

	if (init_type == XEN_HVM_INIT_CANCELLED_SUSPEND)
		return;

	error = xen_hvm_init_hypercall_stubs();

	switch (init_type) {
	case XEN_HVM_INIT_COLD:
		if (error != 0)
			return;

		setup_xen_features();
		break;
	case XEN_HVM_INIT_RESUME:
		if (error != 0)
			panic("Unable to init Xen hypercall stubs on resume");

		/* Clear stale vcpu_info. */
		CPU_FOREACH(i)
			DPCPU_ID_SET(i, vcpu_info, NULL);
		break;
	default:
		panic("Unsupported HVM initialization type");
	}

	xen_vector_callback_enabled = 0;
	xen_domain_type = XEN_HVM_DOMAIN;
	xen_hvm_init_shared_info_page();
	xen_hvm_set_callback(NULL);
	xen_hvm_disable_emulated_devices();
} 

void
xen_hvm_suspend(void)
{
}

void
xen_hvm_resume(bool suspend_cancelled)
{

	xen_hvm_init(suspend_cancelled ?
	    XEN_HVM_INIT_CANCELLED_SUSPEND : XEN_HVM_INIT_RESUME);

	/* Register vcpu_info area for CPU#0. */
	xen_hvm_cpu_init();
}
 
static void
xen_hvm_sysinit(void *arg __unused)
{
	xen_hvm_init(XEN_HVM_INIT_COLD);
}

static void
xen_hvm_cpu_init(void)
{
	struct vcpu_register_vcpu_info info;
	struct vcpu_info *vcpu_info;
	int cpu, rc;

	if (!xen_domain())
		return;

	if (DPCPU_GET(vcpu_info) != NULL) {
		/*
		 * vcpu_info is already set.  We're resuming
		 * from a failed migration and our pre-suspend
		 * configuration is still valid.
		 */
		return;
	}

	vcpu_info = DPCPU_PTR(vcpu_local_info);
	cpu = PCPU_GET(acpi_id);
	info.mfn = vtophys(vcpu_info) >> PAGE_SHIFT;
	info.offset = vtophys(vcpu_info) - trunc_page(vtophys(vcpu_info));

	rc = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
	if (rc != 0)
		DPCPU_SET(vcpu_info, &HYPERVISOR_shared_info->vcpu_info[cpu]);
	else
		DPCPU_SET(vcpu_info, vcpu_info);
}

SYSINIT(xen_hvm_init, SI_SUB_HYPERVISOR, SI_ORDER_FIRST, xen_hvm_sysinit, NULL);
#ifdef SMP
SYSINIT(xen_setup_cpus, SI_SUB_SMP, SI_ORDER_FIRST, xen_setup_cpus, NULL);
#endif
SYSINIT(xen_hvm_cpu_init, SI_SUB_INTR, SI_ORDER_FIRST, xen_hvm_cpu_init, NULL);
OpenPOWER on IntegriCloud