xref: /kernel/linux/linux-5.10/arch/x86/kvm/svm/svm.c (revision 8c2ecf20)
1#define pr_fmt(fmt) "SVM: " fmt
2
3#include <linux/kvm_host.h>
4
5#include "irq.h"
6#include "mmu.h"
7#include "kvm_cache_regs.h"
8#include "x86.h"
9#include "cpuid.h"
10#include "pmu.h"
11
12#include <linux/module.h>
13#include <linux/mod_devicetable.h>
14#include <linux/kernel.h>
15#include <linux/vmalloc.h>
16#include <linux/highmem.h>
17#include <linux/amd-iommu.h>
18#include <linux/sched.h>
19#include <linux/trace_events.h>
20#include <linux/slab.h>
21#include <linux/hashtable.h>
22#include <linux/objtool.h>
23#include <linux/psp-sev.h>
24#include <linux/file.h>
25#include <linux/pagemap.h>
26#include <linux/swap.h>
27#include <linux/rwsem.h>
28
29#include <asm/apic.h>
30#include <asm/perf_event.h>
31#include <asm/tlbflush.h>
32#include <asm/desc.h>
33#include <asm/debugreg.h>
34#include <asm/kvm_para.h>
35#include <asm/irq_remapping.h>
36#include <asm/mce.h>
37#include <asm/spec-ctrl.h>
38#include <asm/cpu_device_id.h>
39
40#include <asm/virtext.h>
41#include "trace.h"
42
43#include "svm.h"
44
45#define __ex(x) __kvm_handle_fault_on_reboot(x)
46
47MODULE_AUTHOR("Qumranet");
48MODULE_LICENSE("GPL");
49
50#ifdef MODULE
51static const struct x86_cpu_id svm_cpu_id[] = {
52	X86_MATCH_FEATURE(X86_FEATURE_SVM, NULL),
53	{}
54};
55MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
56#endif
57
58#define IOPM_ALLOC_ORDER 2
59#define MSRPM_ALLOC_ORDER 1
60
61#define SEG_TYPE_LDT 2
62#define SEG_TYPE_BUSY_TSS16 3
63
64#define SVM_FEATURE_LBRV           (1 <<  1)
65#define SVM_FEATURE_SVML           (1 <<  2)
66#define SVM_FEATURE_TSC_RATE       (1 <<  4)
67#define SVM_FEATURE_VMCB_CLEAN     (1 <<  5)
68#define SVM_FEATURE_FLUSH_ASID     (1 <<  6)
69#define SVM_FEATURE_DECODE_ASSIST  (1 <<  7)
70#define SVM_FEATURE_PAUSE_FILTER   (1 << 10)
71
72#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
73
74#define TSC_RATIO_RSVD          0xffffff0000000000ULL
75#define TSC_RATIO_MIN		0x0000000000000001ULL
76#define TSC_RATIO_MAX		0x000000ffffffffffULL
77
78static bool erratum_383_found __read_mostly;
79
80u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
81
82/*
83 * Set osvw_len to higher value when updated Revision Guides
84 * are published and we know what the new status bits are
85 */
86static uint64_t osvw_len = 4, osvw_status;
87
88static DEFINE_PER_CPU(u64, current_tsc_ratio);
89#define TSC_RATIO_DEFAULT	0x0100000000ULL
90
91static const struct svm_direct_access_msrs {
92	u32 index;   /* Index of the MSR */
93	bool always; /* True if intercept is always on */
94} direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = {
95	{ .index = MSR_STAR,				.always = true  },
96	{ .index = MSR_IA32_SYSENTER_CS,		.always = true  },
97#ifdef CONFIG_X86_64
98	{ .index = MSR_GS_BASE,				.always = true  },
99	{ .index = MSR_FS_BASE,				.always = true  },
100	{ .index = MSR_KERNEL_GS_BASE,			.always = true  },
101	{ .index = MSR_LSTAR,				.always = true  },
102	{ .index = MSR_CSTAR,				.always = true  },
103	{ .index = MSR_SYSCALL_MASK,			.always = true  },
104#endif
105	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
106	{ .index = MSR_IA32_PRED_CMD,			.always = false },
107	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
108	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
109	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
110	{ .index = MSR_IA32_LASTINTTOIP,		.always = false },
111	{ .index = MSR_INVALID,				.always = false },
112};
113
114/* enable NPT for AMD64 and X86 with PAE */
115#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
116bool npt_enabled = true;
117#else
118bool npt_enabled;
119#endif
120
121/*
122 * These 2 parameters are used to config the controls for Pause-Loop Exiting:
123 * pause_filter_count: On processors that support Pause filtering(indicated
124 *	by CPUID Fn8000_000A_EDX), the VMCB provides a 16 bit pause filter
125 *	count value. On VMRUN this value is loaded into an internal counter.
126 *	Each time a pause instruction is executed, this counter is decremented
127 *	until it reaches zero at which time a #VMEXIT is generated if pause
128 *	intercept is enabled. Refer to  AMD APM Vol 2 Section 15.14.4 Pause
129 *	Intercept Filtering for more details.
130 *	This also indicate if ple logic enabled.
131 *
132 * pause_filter_thresh: In addition, some processor families support advanced
133 *	pause filtering (indicated by CPUID Fn8000_000A_EDX) upper bound on
134 *	the amount of time a guest is allowed to execute in a pause loop.
135 *	In this mode, a 16-bit pause filter threshold field is added in the
136 *	VMCB. The threshold value is a cycle count that is used to reset the
137 *	pause counter. As with simple pause filtering, VMRUN loads the pause
138 *	count value from VMCB into an internal counter. Then, on each pause
139 *	instruction the hardware checks the elapsed number of cycles since
140 *	the most recent pause instruction against the pause filter threshold.
141 *	If the elapsed cycle count is greater than the pause filter threshold,
142 *	then the internal pause count is reloaded from the VMCB and execution
143 *	continues. If the elapsed cycle count is less than the pause filter
144 *	threshold, then the internal pause count is decremented. If the count
145 *	value is less than zero and PAUSE intercept is enabled, a #VMEXIT is
146 *	triggered. If advanced pause filtering is supported and pause filter
147 *	threshold field is set to zero, the filter will operate in the simpler,
148 *	count only mode.
149 */
150
151static unsigned short pause_filter_thresh = KVM_DEFAULT_PLE_GAP;
152module_param(pause_filter_thresh, ushort, 0444);
153
154static unsigned short pause_filter_count = KVM_SVM_DEFAULT_PLE_WINDOW;
155module_param(pause_filter_count, ushort, 0444);
156
157/* Default doubles per-vcpu window every exit. */
158static unsigned short pause_filter_count_grow = KVM_DEFAULT_PLE_WINDOW_GROW;
159module_param(pause_filter_count_grow, ushort, 0444);
160
161/* Default resets per-vcpu window every exit to pause_filter_count. */
162static unsigned short pause_filter_count_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK;
163module_param(pause_filter_count_shrink, ushort, 0444);
164
165/* Default is to compute the maximum so we can never overflow. */
166static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX;
167module_param(pause_filter_count_max, ushort, 0444);
168
169/* allow nested paging (virtualized MMU) for all guests */
170static int npt = true;
171module_param(npt, int, S_IRUGO);
172
173/* allow nested virtualization in KVM/SVM */
174static int nested = true;
175module_param(nested, int, S_IRUGO);
176
177/* enable/disable Next RIP Save */
178static int nrips = true;
179module_param(nrips, int, 0444);
180
181/* enable/disable Virtual VMLOAD VMSAVE */
182static int vls = true;
183module_param(vls, int, 0444);
184
185/* enable/disable Virtual GIF */
186static int vgif = true;
187module_param(vgif, int, 0444);
188
189/* enable/disable SEV support */
190static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
191module_param(sev, int, 0444);
192
193static bool __read_mostly dump_invalid_vmcb = 0;
194module_param(dump_invalid_vmcb, bool, 0644);
195
196static u8 rsm_ins_bytes[] = "\x0f\xaa";
197
198static void svm_complete_interrupts(struct vcpu_svm *svm);
199
200static unsigned long iopm_base;
201
202struct kvm_ldttss_desc {
203	u16 limit0;
204	u16 base0;
205	unsigned base1:8, type:5, dpl:2, p:1;
206	unsigned limit1:4, zero0:3, g:1, base2:8;
207	u32 base3;
208	u32 zero1;
209} __attribute__((packed));
210
211DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
212
213static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
214
215#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
216#define MSRS_RANGE_SIZE 2048
217#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
218
219u32 svm_msrpm_offset(u32 msr)
220{
221	u32 offset;
222	int i;
223
224	for (i = 0; i < NUM_MSR_MAPS; i++) {
225		if (msr < msrpm_ranges[i] ||
226		    msr >= msrpm_ranges[i] + MSRS_IN_RANGE)
227			continue;
228
229		offset  = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */
230		offset += (i * MSRS_RANGE_SIZE);       /* add range offset */
231
232		/* Now we have the u8 offset - but need the u32 offset */
233		return offset / 4;
234	}
235
236	/* MSR not in any range */
237	return MSR_INVALID;
238}
239
240#define MAX_INST_SIZE 15
241
242static inline void clgi(void)
243{
244	asm volatile (__ex("clgi"));
245}
246
247static inline void stgi(void)
248{
249	asm volatile (__ex("stgi"));
250}
251
252static inline void invlpga(unsigned long addr, u32 asid)
253{
254	asm volatile (__ex("invlpga %1, %0") : : "c"(asid), "a"(addr));
255}
256
257static int get_max_npt_level(void)
258{
259#ifdef CONFIG_X86_64
260	return PT64_ROOT_4LEVEL;
261#else
262	return PT32E_ROOT_LEVEL;
263#endif
264}
265
266int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
267{
268	struct vcpu_svm *svm = to_svm(vcpu);
269	u64 old_efer = vcpu->arch.efer;
270	vcpu->arch.efer = efer;
271
272	if (!npt_enabled) {
273		/* Shadow paging assumes NX to be available.  */
274		efer |= EFER_NX;
275
276		if (!(efer & EFER_LMA))
277			efer &= ~EFER_LME;
278	}
279
280	if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) {
281		if (!(efer & EFER_SVME)) {
282			svm_leave_nested(vcpu);
283			svm_set_gif(svm, true);
284
285			/*
286			 * Free the nested guest state, unless we are in SMM.
287			 * In this case we will return to the nested guest
288			 * as soon as we leave SMM.
289			 */
290			if (!is_smm(&svm->vcpu))
291				svm_free_nested(svm);
292
293		} else {
294			int ret = svm_allocate_nested(svm);
295
296			if (ret) {
297				vcpu->arch.efer = old_efer;
298				return ret;
299			}
300		}
301	}
302
303	svm->vmcb->save.efer = efer | EFER_SVME;
304	vmcb_mark_dirty(svm->vmcb, VMCB_CR);
305	return 0;
306}
307
308static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu)
309{
310	struct vcpu_svm *svm = to_svm(vcpu);
311	u32 ret = 0;
312
313	if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
314		ret = KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
315	return ret;
316}
317
318static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
319{
320	struct vcpu_svm *svm = to_svm(vcpu);
321
322	if (mask == 0)
323		svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK;
324	else
325		svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK;
326
327}
328
329static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
330{
331	struct vcpu_svm *svm = to_svm(vcpu);
332
333	if (nrips && svm->vmcb->control.next_rip != 0) {
334		WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
335		svm->next_rip = svm->vmcb->control.next_rip;
336	}
337
338	if (!svm->next_rip) {
339		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
340			return 0;
341	} else {
342		kvm_rip_write(vcpu, svm->next_rip);
343	}
344	svm_set_interrupt_shadow(vcpu, 0);
345
346	return 1;
347}
348
349static void svm_queue_exception(struct kvm_vcpu *vcpu)
350{
351	struct vcpu_svm *svm = to_svm(vcpu);
352	unsigned nr = vcpu->arch.exception.nr;
353	bool has_error_code = vcpu->arch.exception.has_error_code;
354	u32 error_code = vcpu->arch.exception.error_code;
355
356	kvm_deliver_exception_payload(&svm->vcpu);
357
358	if (nr == BP_VECTOR && !nrips) {
359		unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
360
361		/*
362		 * For guest debugging where we have to reinject #BP if some
363		 * INT3 is guest-owned:
364		 * Emulate nRIP by moving RIP forward. Will fail if injection
365		 * raises a fault that is not intercepted. Still better than
366		 * failing in all cases.
367		 */
368		(void)skip_emulated_instruction(&svm->vcpu);
369		rip = kvm_rip_read(&svm->vcpu);
370		svm->int3_rip = rip + svm->vmcb->save.cs.base;
371		svm->int3_injected = rip - old_rip;
372	}
373
374	svm->vmcb->control.event_inj = nr
375		| SVM_EVTINJ_VALID
376		| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
377		| SVM_EVTINJ_TYPE_EXEPT;
378	svm->vmcb->control.event_inj_err = error_code;
379}
380
381static void svm_init_erratum_383(void)
382{
383	u32 low, high;
384	int err;
385	u64 val;
386
387	if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH))
388		return;
389
390	/* Use _safe variants to not break nested virtualization */
391	val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
392	if (err)
393		return;
394
395	val |= (1ULL << 47);
396
397	low  = lower_32_bits(val);
398	high = upper_32_bits(val);
399
400	native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
401
402	erratum_383_found = true;
403}
404
405static void svm_init_osvw(struct kvm_vcpu *vcpu)
406{
407	/*
408	 * Guests should see errata 400 and 415 as fixed (assuming that
409	 * HLT and IO instructions are intercepted).
410	 */
411	vcpu->arch.osvw.length = (osvw_len >= 3) ? (osvw_len) : 3;
412	vcpu->arch.osvw.status = osvw_status & ~(6ULL);
413
414	/*
415	 * By increasing VCPU's osvw.length to 3 we are telling the guest that
416	 * all osvw.status bits inside that length, including bit 0 (which is
417	 * reserved for erratum 298), are valid. However, if host processor's
418	 * osvw_len is 0 then osvw_status[0] carries no information. We need to
419	 * be conservative here and therefore we tell the guest that erratum 298
420	 * is present (because we really don't know).
421	 */
422	if (osvw_len == 0 && boot_cpu_data.x86 == 0x10)
423		vcpu->arch.osvw.status |= 1;
424}
425
426static int has_svm(void)
427{
428	const char *msg;
429
430	if (!cpu_has_svm(&msg)) {
431		printk(KERN_INFO "has_svm: %s\n", msg);
432		return 0;
433	}
434
435	if (sev_active()) {
436		pr_info("KVM is unsupported when running as an SEV guest\n");
437		return 0;
438	}
439
440	return 1;
441}
442
443static void svm_hardware_disable(void)
444{
445	/* Make sure we clean up behind us */
446	if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
447		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
448
449	cpu_svm_disable();
450
451	amd_pmu_disable_virt();
452}
453
454static int svm_hardware_enable(void)
455{
456
457	struct svm_cpu_data *sd;
458	uint64_t efer;
459	struct desc_struct *gdt;
460	int me = raw_smp_processor_id();
461
462	rdmsrl(MSR_EFER, efer);
463	if (efer & EFER_SVME)
464		return -EBUSY;
465
466	if (!has_svm()) {
467		pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me);
468		return -EINVAL;
469	}
470	sd = per_cpu(svm_data, me);
471	if (!sd) {
472		pr_err("%s: svm_data is NULL on %d\n", __func__, me);
473		return -EINVAL;
474	}
475
476	sd->asid_generation = 1;
477	sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
478	sd->next_asid = sd->max_asid + 1;
479	sd->min_asid = max_sev_asid + 1;
480
481	gdt = get_current_gdt_rw();
482	sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
483
484	wrmsrl(MSR_EFER, efer | EFER_SVME);
485
486	wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
487
488	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
489		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
490		__this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT);
491	}
492
493
494	/*
495	 * Get OSVW bits.
496	 *
497	 * Note that it is possible to have a system with mixed processor
498	 * revisions and therefore different OSVW bits. If bits are not the same
499	 * on different processors then choose the worst case (i.e. if erratum
500	 * is present on one processor and not on another then assume that the
501	 * erratum is present everywhere).
502	 */
503	if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) {
504		uint64_t len, status = 0;
505		int err;
506
507		len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err);
508		if (!err)
509			status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS,
510						      &err);
511
512		if (err)
513			osvw_status = osvw_len = 0;
514		else {
515			if (len < osvw_len)
516				osvw_len = len;
517			osvw_status |= status;
518			osvw_status &= (1ULL << osvw_len) - 1;
519		}
520	} else
521		osvw_status = osvw_len = 0;
522
523	svm_init_erratum_383();
524
525	amd_pmu_enable_virt();
526
527	return 0;
528}
529
530static void svm_cpu_uninit(int cpu)
531{
532	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
533
534	if (!sd)
535		return;
536
537	per_cpu(svm_data, cpu) = NULL;
538	kfree(sd->sev_vmcbs);
539	__free_page(sd->save_area);
540	kfree(sd);
541}
542
543static int svm_cpu_init(int cpu)
544{
545	struct svm_cpu_data *sd;
546
547	sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
548	if (!sd)
549		return -ENOMEM;
550	sd->cpu = cpu;
551	sd->save_area = alloc_page(GFP_KERNEL);
552	if (!sd->save_area)
553		goto free_cpu_data;
554
555	if (svm_sev_enabled()) {
556		sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
557					      sizeof(void *),
558					      GFP_KERNEL);
559		if (!sd->sev_vmcbs)
560			goto free_save_area;
561	}
562
563	per_cpu(svm_data, cpu) = sd;
564
565	return 0;
566
567free_save_area:
568	__free_page(sd->save_area);
569free_cpu_data:
570	kfree(sd);
571	return -ENOMEM;
572
573}
574
575static int direct_access_msr_slot(u32 msr)
576{
577	u32 i;
578
579	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
580		if (direct_access_msrs[i].index == msr)
581			return i;
582
583	return -ENOENT;
584}
585
586static void set_shadow_msr_intercept(struct kvm_vcpu *vcpu, u32 msr, int read,
587				     int write)
588{
589	struct vcpu_svm *svm = to_svm(vcpu);
590	int slot = direct_access_msr_slot(msr);
591
592	if (slot == -ENOENT)
593		return;
594
595	/* Set the shadow bitmaps to the desired intercept states */
596	if (read)
597		set_bit(slot, svm->shadow_msr_intercept.read);
598	else
599		clear_bit(slot, svm->shadow_msr_intercept.read);
600
601	if (write)
602		set_bit(slot, svm->shadow_msr_intercept.write);
603	else
604		clear_bit(slot, svm->shadow_msr_intercept.write);
605}
606
607static bool valid_msr_intercept(u32 index)
608{
609	return direct_access_msr_slot(index) != -ENOENT;
610}
611
612static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
613{
614	u8 bit_write;
615	unsigned long tmp;
616	u32 offset;
617	u32 *msrpm;
618
619	msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm:
620				      to_svm(vcpu)->msrpm;
621
622	offset    = svm_msrpm_offset(msr);
623	bit_write = 2 * (msr & 0x0f) + 1;
624	tmp       = msrpm[offset];
625
626	BUG_ON(offset == MSR_INVALID);
627
628	return !!test_bit(bit_write,  &tmp);
629}
630
631static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm,
632					u32 msr, int read, int write)
633{
634	u8 bit_read, bit_write;
635	unsigned long tmp;
636	u32 offset;
637
638	/*
639	 * If this warning triggers extend the direct_access_msrs list at the
640	 * beginning of the file
641	 */
642	WARN_ON(!valid_msr_intercept(msr));
643
644	/* Enforce non allowed MSRs to trap */
645	if (read && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
646		read = 0;
647
648	if (write && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
649		write = 0;
650
651	offset    = svm_msrpm_offset(msr);
652	bit_read  = 2 * (msr & 0x0f);
653	bit_write = 2 * (msr & 0x0f) + 1;
654	tmp       = msrpm[offset];
655
656	BUG_ON(offset == MSR_INVALID);
657
658	read  ? clear_bit(bit_read,  &tmp) : set_bit(bit_read,  &tmp);
659	write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp);
660
661	msrpm[offset] = tmp;
662}
663
664static void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
665				 int read, int write)
666{
667	set_shadow_msr_intercept(vcpu, msr, read, write);
668	set_msr_interception_bitmap(vcpu, msrpm, msr, read, write);
669}
670
671u32 *svm_vcpu_alloc_msrpm(void)
672{
673	struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
674	u32 *msrpm;
675
676	if (!pages)
677		return NULL;
678
679	msrpm = page_address(pages);
680	memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
681
682	return msrpm;
683}
684
685void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm)
686{
687	int i;
688
689	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
690		if (!direct_access_msrs[i].always)
691			continue;
692		set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1);
693	}
694}
695
696
697void svm_vcpu_free_msrpm(u32 *msrpm)
698{
699	__free_pages(virt_to_page(msrpm), MSRPM_ALLOC_ORDER);
700}
701
702static void svm_msr_filter_changed(struct kvm_vcpu *vcpu)
703{
704	struct vcpu_svm *svm = to_svm(vcpu);
705	u32 i;
706
707	/*
708	 * Set intercept permissions for all direct access MSRs again. They
709	 * will automatically get filtered through the MSR filter, so we are
710	 * back in sync after this.
711	 */
712	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
713		u32 msr = direct_access_msrs[i].index;
714		u32 read = test_bit(i, svm->shadow_msr_intercept.read);
715		u32 write = test_bit(i, svm->shadow_msr_intercept.write);
716
717		set_msr_interception_bitmap(vcpu, svm->msrpm, msr, read, write);
718	}
719}
720
721static void add_msr_offset(u32 offset)
722{
723	int i;
724
725	for (i = 0; i < MSRPM_OFFSETS; ++i) {
726
727		/* Offset already in list? */
728		if (msrpm_offsets[i] == offset)
729			return;
730
731		/* Slot used by another offset? */
732		if (msrpm_offsets[i] != MSR_INVALID)
733			continue;
734
735		/* Add offset to list */
736		msrpm_offsets[i] = offset;
737
738		return;
739	}
740
741	/*
742	 * If this BUG triggers the msrpm_offsets table has an overflow. Just
743	 * increase MSRPM_OFFSETS in this case.
744	 */
745	BUG();
746}
747
748static void init_msrpm_offsets(void)
749{
750	int i;
751
752	memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets));
753
754	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
755		u32 offset;
756
757		offset = svm_msrpm_offset(direct_access_msrs[i].index);
758		BUG_ON(offset == MSR_INVALID);
759
760		add_msr_offset(offset);
761	}
762}
763
764static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
765{
766	struct vcpu_svm *svm = to_svm(vcpu);
767
768	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
769	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
770	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
771	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
772	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
773}
774
775static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
776{
777	struct vcpu_svm *svm = to_svm(vcpu);
778
779	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
780	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
781	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
782	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
783	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
784}
785
786void disable_nmi_singlestep(struct vcpu_svm *svm)
787{
788	svm->nmi_singlestep = false;
789
790	if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) {
791		/* Clear our flags if they were not set by the guest */
792		if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
793			svm->vmcb->save.rflags &= ~X86_EFLAGS_TF;
794		if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF))
795			svm->vmcb->save.rflags &= ~X86_EFLAGS_RF;
796	}
797}
798
799static void grow_ple_window(struct kvm_vcpu *vcpu)
800{
801	struct vcpu_svm *svm = to_svm(vcpu);
802	struct vmcb_control_area *control = &svm->vmcb->control;
803	int old = control->pause_filter_count;
804
805	control->pause_filter_count = __grow_ple_window(old,
806							pause_filter_count,
807							pause_filter_count_grow,
808							pause_filter_count_max);
809
810	if (control->pause_filter_count != old) {
811		vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
812		trace_kvm_ple_window_update(vcpu->vcpu_id,
813					    control->pause_filter_count, old);
814	}
815}
816
817static void shrink_ple_window(struct kvm_vcpu *vcpu)
818{
819	struct vcpu_svm *svm = to_svm(vcpu);
820	struct vmcb_control_area *control = &svm->vmcb->control;
821	int old = control->pause_filter_count;
822
823	control->pause_filter_count =
824				__shrink_ple_window(old,
825						    pause_filter_count,
826						    pause_filter_count_shrink,
827						    pause_filter_count);
828	if (control->pause_filter_count != old) {
829		vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
830		trace_kvm_ple_window_update(vcpu->vcpu_id,
831					    control->pause_filter_count, old);
832	}
833}
834
835/*
836 * The default MMIO mask is a single bit (excluding the present bit),
837 * which could conflict with the memory encryption bit. Check for
838 * memory encryption support and override the default MMIO mask if
839 * memory encryption is enabled.
840 */
841static __init void svm_adjust_mmio_mask(void)
842{
843	unsigned int enc_bit, mask_bit;
844	u64 msr, mask;
845
846	/* If there is no memory encryption support, use existing mask */
847	if (cpuid_eax(0x80000000) < 0x8000001f)
848		return;
849
850	/* If memory encryption is not enabled, use existing mask */
851	rdmsrl(MSR_K8_SYSCFG, msr);
852	if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
853		return;
854
855	enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
856	mask_bit = boot_cpu_data.x86_phys_bits;
857
858	/* Increment the mask bit if it is the same as the encryption bit */
859	if (enc_bit == mask_bit)
860		mask_bit++;
861
862	/*
863	 * If the mask bit location is below 52, then some bits above the
864	 * physical addressing limit will always be reserved, so use the
865	 * rsvd_bits() function to generate the mask. This mask, along with
866	 * the present bit, will be used to generate a page fault with
867	 * PFER.RSV = 1.
868	 *
869	 * If the mask bit location is 52 (or above), then clear the mask.
870	 */
871	mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
872
873	kvm_mmu_set_mmio_spte_mask(mask, PT_WRITABLE_MASK | PT_USER_MASK);
874}
875
876static void svm_hardware_teardown(void)
877{
878	int cpu;
879
880	if (svm_sev_enabled())
881		sev_hardware_teardown();
882
883	for_each_possible_cpu(cpu)
884		svm_cpu_uninit(cpu);
885
886	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
887	iopm_base = 0;
888}
889
890static __init void svm_set_cpu_caps(void)
891{
892	kvm_set_cpu_caps();
893
894	supported_xss = 0;
895
896	/* CPUID 0x80000001 and 0x8000000A (SVM features) */
897	if (nested) {
898		kvm_cpu_cap_set(X86_FEATURE_SVM);
899
900		if (nrips)
901			kvm_cpu_cap_set(X86_FEATURE_NRIPS);
902
903		if (npt_enabled)
904			kvm_cpu_cap_set(X86_FEATURE_NPT);
905	}
906
907	/* CPUID 0x80000008 */
908	if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
909	    boot_cpu_has(X86_FEATURE_AMD_SSBD))
910		kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD);
911
912	/* Enable INVPCID feature */
913	kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID);
914}
915
916static __init int svm_hardware_setup(void)
917{
918	int cpu;
919	struct page *iopm_pages;
920	void *iopm_va;
921	int r;
922
923	iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER);
924
925	if (!iopm_pages)
926		return -ENOMEM;
927
928	iopm_va = page_address(iopm_pages);
929	memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER));
930	iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
931
932	init_msrpm_offsets();
933
934	supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
935
936	if (boot_cpu_has(X86_FEATURE_NX))
937		kvm_enable_efer_bits(EFER_NX);
938
939	if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
940		kvm_enable_efer_bits(EFER_FFXSR);
941
942	if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) {
943		kvm_has_tsc_control = true;
944		kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX;
945		kvm_tsc_scaling_ratio_frac_bits = 32;
946	}
947
948	/* Check for pause filtering support */
949	if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
950		pause_filter_count = 0;
951		pause_filter_thresh = 0;
952	} else if (!boot_cpu_has(X86_FEATURE_PFTHRESHOLD)) {
953		pause_filter_thresh = 0;
954	}
955
956	if (nested) {
957		printk(KERN_INFO "kvm: Nested Virtualization enabled\n");
958		kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
959	}
960
961	if (sev) {
962		if (boot_cpu_has(X86_FEATURE_SEV) &&
963		    IS_ENABLED(CONFIG_KVM_AMD_SEV)) {
964			r = sev_hardware_setup();
965			if (r)
966				sev = false;
967		} else {
968			sev = false;
969		}
970	}
971
972	svm_adjust_mmio_mask();
973
974	for_each_possible_cpu(cpu) {
975		r = svm_cpu_init(cpu);
976		if (r)
977			goto err;
978	}
979
980	if (!boot_cpu_has(X86_FEATURE_NPT))
981		npt_enabled = false;
982
983	if (npt_enabled && !npt)
984		npt_enabled = false;
985
986	kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G);
987	pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
988
989	if (nrips) {
990		if (!boot_cpu_has(X86_FEATURE_NRIPS))
991			nrips = false;
992	}
993
994	if (avic) {
995		if (!npt_enabled ||
996		    !boot_cpu_has(X86_FEATURE_AVIC) ||
997		    !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) {
998			avic = false;
999		} else {
1000			pr_info("AVIC enabled\n");
1001
1002			amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
1003		}
1004	}
1005
1006	if (vls) {
1007		if (!npt_enabled ||
1008		    !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
1009		    !IS_ENABLED(CONFIG_X86_64)) {
1010			vls = false;
1011		} else {
1012			pr_info("Virtual VMLOAD VMSAVE supported\n");
1013		}
1014	}
1015
1016	if (vgif) {
1017		if (!boot_cpu_has(X86_FEATURE_VGIF))
1018			vgif = false;
1019		else
1020			pr_info("Virtual GIF supported\n");
1021	}
1022
1023	svm_set_cpu_caps();
1024
1025	/*
1026	 * It seems that on AMD processors PTE's accessed bit is
1027	 * being set by the CPU hardware before the NPF vmexit.
1028	 * This is not expected behaviour and our tests fail because
1029	 * of it.
1030	 * A workaround here is to disable support for
1031	 * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled.
1032	 * In this case userspace can know if there is support using
1033	 * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle
1034	 * it
1035	 * If future AMD CPU models change the behaviour described above,
1036	 * this variable can be changed accordingly
1037	 */
1038	allow_smaller_maxphyaddr = !npt_enabled;
1039
1040	return 0;
1041
1042err:
1043	svm_hardware_teardown();
1044	return r;
1045}
1046
1047static void init_seg(struct vmcb_seg *seg)
1048{
1049	seg->selector = 0;
1050	seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK |
1051		      SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
1052	seg->limit = 0xffff;
1053	seg->base = 0;
1054}
1055
1056static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
1057{
1058	seg->selector = 0;
1059	seg->attrib = SVM_SELECTOR_P_MASK | type;
1060	seg->limit = 0xffff;
1061	seg->base = 0;
1062}
1063
1064static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
1065{
1066	struct vcpu_svm *svm = to_svm(vcpu);
1067	u64 g_tsc_offset = 0;
1068
1069	if (is_guest_mode(vcpu)) {
1070		/* Write L1's TSC offset.  */
1071		g_tsc_offset = svm->vmcb->control.tsc_offset -
1072			       svm->nested.hsave->control.tsc_offset;
1073		svm->nested.hsave->control.tsc_offset = offset;
1074	}
1075
1076	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
1077				   svm->vmcb->control.tsc_offset - g_tsc_offset,
1078				   offset);
1079
1080	svm->vmcb->control.tsc_offset = offset + g_tsc_offset;
1081
1082	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
1083	return svm->vmcb->control.tsc_offset;
1084}
1085
1086static void svm_check_invpcid(struct vcpu_svm *svm)
1087{
1088	/*
1089	 * Intercept INVPCID if shadow paging is enabled to sync/free shadow
1090	 * roots, or if INVPCID is disabled in the guest to inject #UD.
1091	 */
1092	if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) {
1093		if (!npt_enabled ||
1094		    !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID))
1095			svm_set_intercept(svm, INTERCEPT_INVPCID);
1096		else
1097			svm_clr_intercept(svm, INTERCEPT_INVPCID);
1098	}
1099}
1100
1101static void init_vmcb(struct vcpu_svm *svm)
1102{
1103	struct vmcb_control_area *control = &svm->vmcb->control;
1104	struct vmcb_save_area *save = &svm->vmcb->save;
1105
1106	svm->vcpu.arch.hflags = 0;
1107
1108	svm_set_intercept(svm, INTERCEPT_CR0_READ);
1109	svm_set_intercept(svm, INTERCEPT_CR3_READ);
1110	svm_set_intercept(svm, INTERCEPT_CR4_READ);
1111	svm_set_intercept(svm, INTERCEPT_CR0_WRITE);
1112	svm_set_intercept(svm, INTERCEPT_CR3_WRITE);
1113	svm_set_intercept(svm, INTERCEPT_CR4_WRITE);
1114	if (!kvm_vcpu_apicv_active(&svm->vcpu))
1115		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
1116
1117	set_dr_intercepts(svm);
1118
1119	set_exception_intercept(svm, PF_VECTOR);
1120	set_exception_intercept(svm, UD_VECTOR);
1121	set_exception_intercept(svm, MC_VECTOR);
1122	set_exception_intercept(svm, AC_VECTOR);
1123	set_exception_intercept(svm, DB_VECTOR);
1124	/*
1125	 * Guest access to VMware backdoor ports could legitimately
1126	 * trigger #GP because of TSS I/O permission bitmap.
1127	 * We intercept those #GP and allow access to them anyway
1128	 * as VMware does.
1129	 */
1130	if (enable_vmware_backdoor)
1131		set_exception_intercept(svm, GP_VECTOR);
1132
1133	svm_set_intercept(svm, INTERCEPT_INTR);
1134	svm_set_intercept(svm, INTERCEPT_NMI);
1135	svm_set_intercept(svm, INTERCEPT_SMI);
1136	svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0);
1137	svm_set_intercept(svm, INTERCEPT_RDPMC);
1138	svm_set_intercept(svm, INTERCEPT_CPUID);
1139	svm_set_intercept(svm, INTERCEPT_INVD);
1140	svm_set_intercept(svm, INTERCEPT_INVLPG);
1141	svm_set_intercept(svm, INTERCEPT_INVLPGA);
1142	svm_set_intercept(svm, INTERCEPT_IOIO_PROT);
1143	svm_set_intercept(svm, INTERCEPT_MSR_PROT);
1144	svm_set_intercept(svm, INTERCEPT_TASK_SWITCH);
1145	svm_set_intercept(svm, INTERCEPT_SHUTDOWN);
1146	svm_set_intercept(svm, INTERCEPT_VMRUN);
1147	svm_set_intercept(svm, INTERCEPT_VMMCALL);
1148	svm_set_intercept(svm, INTERCEPT_VMLOAD);
1149	svm_set_intercept(svm, INTERCEPT_VMSAVE);
1150	svm_set_intercept(svm, INTERCEPT_STGI);
1151	svm_set_intercept(svm, INTERCEPT_CLGI);
1152	svm_set_intercept(svm, INTERCEPT_SKINIT);
1153	svm_set_intercept(svm, INTERCEPT_WBINVD);
1154	svm_set_intercept(svm, INTERCEPT_XSETBV);
1155	svm_set_intercept(svm, INTERCEPT_RDPRU);
1156	svm_set_intercept(svm, INTERCEPT_RSM);
1157
1158	if (!kvm_mwait_in_guest(svm->vcpu.kvm)) {
1159		svm_set_intercept(svm, INTERCEPT_MONITOR);
1160		svm_set_intercept(svm, INTERCEPT_MWAIT);
1161	}
1162
1163	if (!kvm_hlt_in_guest(svm->vcpu.kvm))
1164		svm_set_intercept(svm, INTERCEPT_HLT);
1165
1166	control->iopm_base_pa = __sme_set(iopm_base);
1167	control->msrpm_base_pa = __sme_set(__pa(svm->msrpm));
1168	control->int_ctl = V_INTR_MASKING_MASK;
1169
1170	init_seg(&save->es);
1171	init_seg(&save->ss);
1172	init_seg(&save->ds);
1173	init_seg(&save->fs);
1174	init_seg(&save->gs);
1175
1176	save->cs.selector = 0xf000;
1177	save->cs.base = 0xffff0000;
1178	/* Executable/Readable Code Segment */
1179	save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK |
1180		SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK;
1181	save->cs.limit = 0xffff;
1182
1183	save->gdtr.limit = 0xffff;
1184	save->idtr.limit = 0xffff;
1185
1186	init_sys_seg(&save->ldtr, SEG_TYPE_LDT);
1187	init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16);
1188
1189	svm_set_cr4(&svm->vcpu, 0);
1190	svm_set_efer(&svm->vcpu, 0);
1191	save->dr6 = 0xffff0ff0;
1192	kvm_set_rflags(&svm->vcpu, 2);
1193	save->rip = 0x0000fff0;
1194	svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
1195
1196	/*
1197	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
1198	 * It also updates the guest-visible cr0 value.
1199	 */
1200	svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
1201	kvm_mmu_reset_context(&svm->vcpu);
1202
1203	save->cr4 = X86_CR4_PAE;
1204	/* rdx = ?? */
1205
1206	if (npt_enabled) {
1207		/* Setup VMCB for Nested Paging */
1208		control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE;
1209		svm_clr_intercept(svm, INTERCEPT_INVLPG);
1210		clr_exception_intercept(svm, PF_VECTOR);
1211		svm_clr_intercept(svm, INTERCEPT_CR3_READ);
1212		svm_clr_intercept(svm, INTERCEPT_CR3_WRITE);
1213		save->g_pat = svm->vcpu.arch.pat;
1214		save->cr3 = 0;
1215		save->cr4 = 0;
1216	}
1217	svm->asid_generation = 0;
1218
1219	svm->nested.vmcb12_gpa = 0;
1220	svm->vcpu.arch.hflags = 0;
1221
1222	if (!kvm_pause_in_guest(svm->vcpu.kvm)) {
1223		control->pause_filter_count = pause_filter_count;
1224		if (pause_filter_thresh)
1225			control->pause_filter_thresh = pause_filter_thresh;
1226		svm_set_intercept(svm, INTERCEPT_PAUSE);
1227	} else {
1228		svm_clr_intercept(svm, INTERCEPT_PAUSE);
1229	}
1230
1231	svm_check_invpcid(svm);
1232
1233	if (kvm_vcpu_apicv_active(&svm->vcpu))
1234		avic_init_vmcb(svm);
1235
1236	/*
1237	 * If hardware supports Virtual VMLOAD VMSAVE then enable it
1238	 * in VMCB and clear intercepts to avoid #VMEXIT.
1239	 */
1240	if (vls) {
1241		svm_clr_intercept(svm, INTERCEPT_VMLOAD);
1242		svm_clr_intercept(svm, INTERCEPT_VMSAVE);
1243		svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
1244	}
1245
1246	if (vgif) {
1247		svm_clr_intercept(svm, INTERCEPT_STGI);
1248		svm_clr_intercept(svm, INTERCEPT_CLGI);
1249		svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK;
1250	}
1251
1252	if (sev_guest(svm->vcpu.kvm)) {
1253		svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE;
1254		clr_exception_intercept(svm, UD_VECTOR);
1255	}
1256
1257	vmcb_mark_all_dirty(svm->vmcb);
1258
1259	enable_gif(svm);
1260
1261}
1262
1263static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
1264{
1265	struct vcpu_svm *svm = to_svm(vcpu);
1266	u32 dummy;
1267	u32 eax = 1;
1268
1269	svm->spec_ctrl = 0;
1270	svm->virt_spec_ctrl = 0;
1271
1272	if (!init_event) {
1273		svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
1274					   MSR_IA32_APICBASE_ENABLE;
1275		if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
1276			svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
1277	}
1278	init_vmcb(svm);
1279
1280	kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, false);
1281	kvm_rdx_write(vcpu, eax);
1282
1283	if (kvm_vcpu_apicv_active(vcpu) && !init_event)
1284		avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE);
1285}
1286
1287static int svm_create_vcpu(struct kvm_vcpu *vcpu)
1288{
1289	struct vcpu_svm *svm;
1290	struct page *vmcb_page;
1291	int err;
1292
1293	BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0);
1294	svm = to_svm(vcpu);
1295
1296	err = -ENOMEM;
1297	vmcb_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
1298	if (!vmcb_page)
1299		goto out;
1300
1301	err = avic_init_vcpu(svm);
1302	if (err)
1303		goto error_free_vmcb_page;
1304
1305	/* We initialize this flag to true to make sure that the is_running
1306	 * bit would be set the first time the vcpu is loaded.
1307	 */
1308	if (irqchip_in_kernel(vcpu->kvm) && kvm_apicv_activated(vcpu->kvm))
1309		svm->avic_is_running = true;
1310
1311	svm->msrpm = svm_vcpu_alloc_msrpm();
1312	if (!svm->msrpm) {
1313		err = -ENOMEM;
1314		goto error_free_vmcb_page;
1315	}
1316
1317	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
1318
1319	svm->vmcb = page_address(vmcb_page);
1320	svm->vmcb_pa = __sme_set(page_to_pfn(vmcb_page) << PAGE_SHIFT);
1321	svm->asid_generation = 0;
1322	init_vmcb(svm);
1323
1324	svm_init_osvw(vcpu);
1325	vcpu->arch.microcode_version = 0x01000065;
1326
1327	return 0;
1328
1329error_free_vmcb_page:
1330	__free_page(vmcb_page);
1331out:
1332	return err;
1333}
1334
1335static void svm_clear_current_vmcb(struct vmcb *vmcb)
1336{
1337	int i;
1338
1339	for_each_online_cpu(i)
1340		cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL);
1341}
1342
1343static void svm_free_vcpu(struct kvm_vcpu *vcpu)
1344{
1345	struct vcpu_svm *svm = to_svm(vcpu);
1346
1347	/*
1348	 * The vmcb page can be recycled, causing a false negative in
1349	 * svm_vcpu_load(). So, ensure that no logical CPU has this
1350	 * vmcb page recorded as its current vmcb.
1351	 */
1352	svm_clear_current_vmcb(svm->vmcb);
1353
1354	svm_leave_nested(vcpu);
1355	svm_free_nested(svm);
1356
1357	__free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT));
1358	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
1359}
1360
1361static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
1362{
1363	struct vcpu_svm *svm = to_svm(vcpu);
1364	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
1365	int i;
1366
1367	if (unlikely(cpu != vcpu->cpu)) {
1368		svm->asid_generation = 0;
1369		vmcb_mark_all_dirty(svm->vmcb);
1370	}
1371
1372#ifdef CONFIG_X86_64
1373	rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host.gs_base);
1374#endif
1375	savesegment(fs, svm->host.fs);
1376	savesegment(gs, svm->host.gs);
1377	svm->host.ldt = kvm_read_ldt();
1378
1379	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
1380		rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
1381
1382	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
1383		u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio;
1384		if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
1385			__this_cpu_write(current_tsc_ratio, tsc_ratio);
1386			wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
1387		}
1388	}
1389	/* This assumes that the kernel never uses MSR_TSC_AUX */
1390	if (static_cpu_has(X86_FEATURE_RDTSCP))
1391		wrmsrl(MSR_TSC_AUX, svm->tsc_aux);
1392
1393	if (sd->current_vmcb != svm->vmcb) {
1394		sd->current_vmcb = svm->vmcb;
1395
1396		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT))
1397			indirect_branch_prediction_barrier();
1398	}
1399	avic_vcpu_load(vcpu, cpu);
1400}
1401
1402static void svm_vcpu_put(struct kvm_vcpu *vcpu)
1403{
1404	struct vcpu_svm *svm = to_svm(vcpu);
1405	int i;
1406
1407	avic_vcpu_put(vcpu);
1408
1409	++vcpu->stat.host_state_reload;
1410	kvm_load_ldt(svm->host.ldt);
1411#ifdef CONFIG_X86_64
1412	loadsegment(fs, svm->host.fs);
1413	wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase);
1414	load_gs_index(svm->host.gs);
1415#else
1416#ifdef CONFIG_X86_32_LAZY_GS
1417	loadsegment(gs, svm->host.gs);
1418#endif
1419#endif
1420	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
1421		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
1422}
1423
1424static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
1425{
1426	struct vcpu_svm *svm = to_svm(vcpu);
1427	unsigned long rflags = svm->vmcb->save.rflags;
1428
1429	if (svm->nmi_singlestep) {
1430		/* Hide our flags if they were not set by the guest */
1431		if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
1432			rflags &= ~X86_EFLAGS_TF;
1433		if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF))
1434			rflags &= ~X86_EFLAGS_RF;
1435	}
1436	return rflags;
1437}
1438
1439static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
1440{
1441	if (to_svm(vcpu)->nmi_singlestep)
1442		rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
1443
1444       /*
1445        * Any change of EFLAGS.VM is accompanied by a reload of SS
1446        * (caused by either a task switch or an inter-privilege IRET),
1447        * so we do not need to update the CPL here.
1448        */
1449	to_svm(vcpu)->vmcb->save.rflags = rflags;
1450}
1451
1452static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
1453{
1454	switch (reg) {
1455	case VCPU_EXREG_PDPTR:
1456		BUG_ON(!npt_enabled);
1457		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
1458		break;
1459	default:
1460		WARN_ON_ONCE(1);
1461	}
1462}
1463
1464static void svm_set_vintr(struct vcpu_svm *svm)
1465{
1466	struct vmcb_control_area *control;
1467
1468	/* The following fields are ignored when AVIC is enabled */
1469	WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu));
1470	svm_set_intercept(svm, INTERCEPT_VINTR);
1471
1472	/*
1473	 * This is just a dummy VINTR to actually cause a vmexit to happen.
1474	 * Actual injection of virtual interrupts happens through EVENTINJ.
1475	 */
1476	control = &svm->vmcb->control;
1477	control->int_vector = 0x0;
1478	control->int_ctl &= ~V_INTR_PRIO_MASK;
1479	control->int_ctl |= V_IRQ_MASK |
1480		((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT);
1481	vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
1482}
1483
1484static void svm_clear_vintr(struct vcpu_svm *svm)
1485{
1486	svm_clr_intercept(svm, INTERCEPT_VINTR);
1487
1488	/* Drop int_ctl fields related to VINTR injection.  */
1489	svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
1490	if (is_guest_mode(&svm->vcpu)) {
1491		svm->nested.hsave->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
1492
1493		WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) !=
1494			(svm->nested.ctl.int_ctl & V_TPR_MASK));
1495		svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
1496			V_IRQ_INJECTION_BITS_MASK;
1497
1498		svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
1499	}
1500
1501	vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
1502}
1503
1504static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg)
1505{
1506	struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save;
1507
1508	switch (seg) {
1509	case VCPU_SREG_CS: return &save->cs;
1510	case VCPU_SREG_DS: return &save->ds;
1511	case VCPU_SREG_ES: return &save->es;
1512	case VCPU_SREG_FS: return &save->fs;
1513	case VCPU_SREG_GS: return &save->gs;
1514	case VCPU_SREG_SS: return &save->ss;
1515	case VCPU_SREG_TR: return &save->tr;
1516	case VCPU_SREG_LDTR: return &save->ldtr;
1517	}
1518	BUG();
1519	return NULL;
1520}
1521
1522static u64 svm_get_segment_base(struct kvm_vcpu *vcpu, int seg)
1523{
1524	struct vmcb_seg *s = svm_seg(vcpu, seg);
1525
1526	return s->base;
1527}
1528
1529static void svm_get_segment(struct kvm_vcpu *vcpu,
1530			    struct kvm_segment *var, int seg)
1531{
1532	struct vmcb_seg *s = svm_seg(vcpu, seg);
1533
1534	var->base = s->base;
1535	var->limit = s->limit;
1536	var->selector = s->selector;
1537	var->type = s->attrib & SVM_SELECTOR_TYPE_MASK;
1538	var->s = (s->attrib >> SVM_SELECTOR_S_SHIFT) & 1;
1539	var->dpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
1540	var->present = (s->attrib >> SVM_SELECTOR_P_SHIFT) & 1;
1541	var->avl = (s->attrib >> SVM_SELECTOR_AVL_SHIFT) & 1;
1542	var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1;
1543	var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
1544
1545	/*
1546	 * AMD CPUs circa 2014 track the G bit for all segments except CS.
1547	 * However, the SVM spec states that the G bit is not observed by the
1548	 * CPU, and some VMware virtual CPUs drop the G bit for all segments.
1549	 * So let's synthesize a legal G bit for all segments, this helps
1550	 * running KVM nested. It also helps cross-vendor migration, because
1551	 * Intel's vmentry has a check on the 'G' bit.
1552	 */
1553	var->g = s->limit > 0xfffff;
1554
1555	/*
1556	 * AMD's VMCB does not have an explicit unusable field, so emulate it
1557	 * for cross vendor migration purposes by "not present"
1558	 */
1559	var->unusable = !var->present;
1560
1561	switch (seg) {
1562	case VCPU_SREG_TR:
1563		/*
1564		 * Work around a bug where the busy flag in the tr selector
1565		 * isn't exposed
1566		 */
1567		var->type |= 0x2;
1568		break;
1569	case VCPU_SREG_DS:
1570	case VCPU_SREG_ES:
1571	case VCPU_SREG_FS:
1572	case VCPU_SREG_GS:
1573		/*
1574		 * The accessed bit must always be set in the segment
1575		 * descriptor cache, although it can be cleared in the
1576		 * descriptor, the cached bit always remains at 1. Since
1577		 * Intel has a check on this, set it here to support
1578		 * cross-vendor migration.
1579		 */
1580		if (!var->unusable)
1581			var->type |= 0x1;
1582		break;
1583	case VCPU_SREG_SS:
1584		/*
1585		 * On AMD CPUs sometimes the DB bit in the segment
1586		 * descriptor is left as 1, although the whole segment has
1587		 * been made unusable. Clear it here to pass an Intel VMX
1588		 * entry check when cross vendor migrating.
1589		 */
1590		if (var->unusable)
1591			var->db = 0;
1592		/* This is symmetric with svm_set_segment() */
1593		var->dpl = to_svm(vcpu)->vmcb->save.cpl;
1594		break;
1595	}
1596}
1597
1598static int svm_get_cpl(struct kvm_vcpu *vcpu)
1599{
1600	struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save;
1601
1602	return save->cpl;
1603}
1604
1605static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
1606{
1607	struct vcpu_svm *svm = to_svm(vcpu);
1608
1609	dt->size = svm->vmcb->save.idtr.limit;
1610	dt->address = svm->vmcb->save.idtr.base;
1611}
1612
1613static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
1614{
1615	struct vcpu_svm *svm = to_svm(vcpu);
1616
1617	svm->vmcb->save.idtr.limit = dt->size;
1618	svm->vmcb->save.idtr.base = dt->address ;
1619	vmcb_mark_dirty(svm->vmcb, VMCB_DT);
1620}
1621
1622static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
1623{
1624	struct vcpu_svm *svm = to_svm(vcpu);
1625
1626	dt->size = svm->vmcb->save.gdtr.limit;
1627	dt->address = svm->vmcb->save.gdtr.base;
1628}
1629
1630static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
1631{
1632	struct vcpu_svm *svm = to_svm(vcpu);
1633
1634	svm->vmcb->save.gdtr.limit = dt->size;
1635	svm->vmcb->save.gdtr.base = dt->address ;
1636	vmcb_mark_dirty(svm->vmcb, VMCB_DT);
1637}
1638
1639static void update_cr0_intercept(struct vcpu_svm *svm)
1640{
1641	ulong gcr0 = svm->vcpu.arch.cr0;
1642	u64 *hcr0 = &svm->vmcb->save.cr0;
1643
1644	*hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK)
1645		| (gcr0 & SVM_CR0_SELECTIVE_MASK);
1646
1647	vmcb_mark_dirty(svm->vmcb, VMCB_CR);
1648
1649	if (gcr0 == *hcr0) {
1650		svm_clr_intercept(svm, INTERCEPT_CR0_READ);
1651		svm_clr_intercept(svm, INTERCEPT_CR0_WRITE);
1652	} else {
1653		svm_set_intercept(svm, INTERCEPT_CR0_READ);
1654		svm_set_intercept(svm, INTERCEPT_CR0_WRITE);
1655	}
1656}
1657
1658void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
1659{
1660	struct vcpu_svm *svm = to_svm(vcpu);
1661
1662#ifdef CONFIG_X86_64
1663	if (vcpu->arch.efer & EFER_LME) {
1664		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
1665			vcpu->arch.efer |= EFER_LMA;
1666			svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
1667		}
1668
1669		if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) {
1670			vcpu->arch.efer &= ~EFER_LMA;
1671			svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
1672		}
1673	}
1674#endif
1675	vcpu->arch.cr0 = cr0;
1676
1677	if (!npt_enabled)
1678		cr0 |= X86_CR0_PG | X86_CR0_WP;
1679
1680	/*
1681	 * re-enable caching here because the QEMU bios
1682	 * does not do it - this results in some delay at
1683	 * reboot
1684	 */
1685	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
1686		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
1687	svm->vmcb->save.cr0 = cr0;
1688	vmcb_mark_dirty(svm->vmcb, VMCB_CR);
1689	update_cr0_intercept(svm);
1690}
1691
1692static bool svm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
1693{
1694	return true;
1695}
1696
1697void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
1698{
1699	unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE;
1700	unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4;
1701
1702	if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
1703		svm_flush_tlb(vcpu);
1704
1705	vcpu->arch.cr4 = cr4;
1706	if (!npt_enabled)
1707		cr4 |= X86_CR4_PAE;
1708	cr4 |= host_cr4_mce;
1709	to_svm(vcpu)->vmcb->save.cr4 = cr4;
1710	vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
1711}
1712
1713static void svm_set_segment(struct kvm_vcpu *vcpu,
1714			    struct kvm_segment *var, int seg)
1715{
1716	struct vcpu_svm *svm = to_svm(vcpu);
1717	struct vmcb_seg *s = svm_seg(vcpu, seg);
1718
1719	s->base = var->base;
1720	s->limit = var->limit;
1721	s->selector = var->selector;
1722	s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
1723	s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
1724	s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
1725	s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT;
1726	s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
1727	s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
1728	s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
1729	s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
1730
1731	/*
1732	 * This is always accurate, except if SYSRET returned to a segment
1733	 * with SS.DPL != 3.  Intel does not have this quirk, and always
1734	 * forces SS.DPL to 3 on sysret, so we ignore that case; fixing it
1735	 * would entail passing the CPL to userspace and back.
1736	 */
1737	if (seg == VCPU_SREG_SS)
1738		/* This is symmetric with svm_get_segment() */
1739		svm->vmcb->save.cpl = (var->dpl & 3);
1740
1741	vmcb_mark_dirty(svm->vmcb, VMCB_SEG);
1742}
1743
1744static void update_exception_bitmap(struct kvm_vcpu *vcpu)
1745{
1746	struct vcpu_svm *svm = to_svm(vcpu);
1747
1748	clr_exception_intercept(svm, BP_VECTOR);
1749
1750	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
1751		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
1752			set_exception_intercept(svm, BP_VECTOR);
1753	}
1754}
1755
1756static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
1757{
1758	if (sd->next_asid > sd->max_asid) {
1759		++sd->asid_generation;
1760		sd->next_asid = sd->min_asid;
1761		svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
1762	}
1763
1764	svm->asid_generation = sd->asid_generation;
1765	svm->vmcb->control.asid = sd->next_asid++;
1766
1767	vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
1768}
1769
1770static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value)
1771{
1772	struct vmcb *vmcb = svm->vmcb;
1773
1774	if (unlikely(value != vmcb->save.dr6)) {
1775		vmcb->save.dr6 = value;
1776		vmcb_mark_dirty(vmcb, VMCB_DR);
1777	}
1778}
1779
1780static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
1781{
1782	struct vcpu_svm *svm = to_svm(vcpu);
1783
1784	get_debugreg(vcpu->arch.db[0], 0);
1785	get_debugreg(vcpu->arch.db[1], 1);
1786	get_debugreg(vcpu->arch.db[2], 2);
1787	get_debugreg(vcpu->arch.db[3], 3);
1788	/*
1789	 * We cannot reset svm->vmcb->save.dr6 to DR6_FIXED_1|DR6_RTM here,
1790	 * because db_interception might need it.  We can do it before vmentry.
1791	 */
1792	vcpu->arch.dr6 = svm->vmcb->save.dr6;
1793	vcpu->arch.dr7 = svm->vmcb->save.dr7;
1794	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
1795	set_dr_intercepts(svm);
1796}
1797
1798static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
1799{
1800	struct vcpu_svm *svm = to_svm(vcpu);
1801
1802	svm->vmcb->save.dr7 = value;
1803	vmcb_mark_dirty(svm->vmcb, VMCB_DR);
1804}
1805
1806static int pf_interception(struct vcpu_svm *svm)
1807{
1808	u64 fault_address = svm->vmcb->control.exit_info_2;
1809	u64 error_code = svm->vmcb->control.exit_info_1;
1810
1811	return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address,
1812			static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
1813			svm->vmcb->control.insn_bytes : NULL,
1814			svm->vmcb->control.insn_len);
1815}
1816
1817static int npf_interception(struct vcpu_svm *svm)
1818{
1819	u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2);
1820	u64 error_code = svm->vmcb->control.exit_info_1;
1821
1822	trace_kvm_page_fault(fault_address, error_code);
1823	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code,
1824			static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
1825			svm->vmcb->control.insn_bytes : NULL,
1826			svm->vmcb->control.insn_len);
1827}
1828
1829static int db_interception(struct vcpu_svm *svm)
1830{
1831	struct kvm_run *kvm_run = svm->vcpu.run;
1832	struct kvm_vcpu *vcpu = &svm->vcpu;
1833
1834	if (!(svm->vcpu.guest_debug &
1835	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
1836		!svm->nmi_singlestep) {
1837		u32 payload = (svm->vmcb->save.dr6 ^ DR6_RTM) & ~DR6_FIXED_1;
1838		kvm_queue_exception_p(&svm->vcpu, DB_VECTOR, payload);
1839		return 1;
1840	}
1841
1842	if (svm->nmi_singlestep) {
1843		disable_nmi_singlestep(svm);
1844		/* Make sure we check for pending NMIs upon entry */
1845		kvm_make_request(KVM_REQ_EVENT, vcpu);
1846	}
1847
1848	if (svm->vcpu.guest_debug &
1849	    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
1850		kvm_run->exit_reason = KVM_EXIT_DEBUG;
1851		kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6;
1852		kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7;
1853		kvm_run->debug.arch.pc =
1854			svm->vmcb->save.cs.base + svm->vmcb->save.rip;
1855		kvm_run->debug.arch.exception = DB_VECTOR;
1856		return 0;
1857	}
1858
1859	return 1;
1860}
1861
1862static int bp_interception(struct vcpu_svm *svm)
1863{
1864	struct kvm_run *kvm_run = svm->vcpu.run;
1865
1866	kvm_run->exit_reason = KVM_EXIT_DEBUG;
1867	kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
1868	kvm_run->debug.arch.exception = BP_VECTOR;
1869	return 0;
1870}
1871
1872static int ud_interception(struct vcpu_svm *svm)
1873{
1874	return handle_ud(&svm->vcpu);
1875}
1876
1877static int ac_interception(struct vcpu_svm *svm)
1878{
1879	kvm_queue_exception_e(&svm->vcpu, AC_VECTOR, 0);
1880	return 1;
1881}
1882
1883static int gp_interception(struct vcpu_svm *svm)
1884{
1885	struct kvm_vcpu *vcpu = &svm->vcpu;
1886	u32 error_code = svm->vmcb->control.exit_info_1;
1887
1888	WARN_ON_ONCE(!enable_vmware_backdoor);
1889
1890	/*
1891	 * VMware backdoor emulation on #GP interception only handles IN{S},
1892	 * OUT{S}, and RDPMC, none of which generate a non-zero error code.
1893	 */
1894	if (error_code) {
1895		kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
1896		return 1;
1897	}
1898	return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP);
1899}
1900
1901static bool is_erratum_383(void)
1902{
1903	int err, i;
1904	u64 value;
1905
1906	if (!erratum_383_found)
1907		return false;
1908
1909	value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
1910	if (err)
1911		return false;
1912
1913	/* Bit 62 may or may not be set for this mce */
1914	value &= ~(1ULL << 62);
1915
1916	if (value != 0xb600000000010015ULL)
1917		return false;
1918
1919	/* Clear MCi_STATUS registers */
1920	for (i = 0; i < 6; ++i)
1921		native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
1922
1923	value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
1924	if (!err) {
1925		u32 low, high;
1926
1927		value &= ~(1ULL << 2);
1928		low    = lower_32_bits(value);
1929		high   = upper_32_bits(value);
1930
1931		native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
1932	}
1933
1934	/* Flush tlb to evict multi-match entries */
1935	__flush_tlb_all();
1936
1937	return true;
1938}
1939
1940/*
1941 * Trigger machine check on the host. We assume all the MSRs are already set up
1942 * by the CPU and that we still run on the same CPU as the MCE occurred on.
1943 * We pass a fake environment to the machine check handler because we want
1944 * the guest to be always treated like user space, no matter what context
1945 * it used internally.
1946 */
1947static void kvm_machine_check(void)
1948{
1949#if defined(CONFIG_X86_MCE)
1950	struct pt_regs regs = {
1951		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
1952		.flags = X86_EFLAGS_IF,
1953	};
1954
1955	do_machine_check(&regs);
1956#endif
1957}
1958
1959static void svm_handle_mce(struct vcpu_svm *svm)
1960{
1961	if (is_erratum_383()) {
1962		/*
1963		 * Erratum 383 triggered. Guest state is corrupt so kill the
1964		 * guest.
1965		 */
1966		pr_err("KVM: Guest triggered AMD Erratum 383\n");
1967
1968		kvm_make_request(KVM_REQ_TRIPLE_FAULT, &svm->vcpu);
1969
1970		return;
1971	}
1972
1973	/*
1974	 * On an #MC intercept the MCE handler is not called automatically in
1975	 * the host. So do it by hand here.
1976	 */
1977	kvm_machine_check();
1978}
1979
1980static int mc_interception(struct vcpu_svm *svm)
1981{
1982	return 1;
1983}
1984
1985static int shutdown_interception(struct vcpu_svm *svm)
1986{
1987	struct kvm_run *kvm_run = svm->vcpu.run;
1988
1989	/*
1990	 * VMCB is undefined after a SHUTDOWN intercept
1991	 * so reinitialize it.
1992	 */
1993	clear_page(svm->vmcb);
1994	init_vmcb(svm);
1995
1996	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
1997	return 0;
1998}
1999
2000static int io_interception(struct vcpu_svm *svm)
2001{
2002	struct kvm_vcpu *vcpu = &svm->vcpu;
2003	u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
2004	int size, in, string;
2005	unsigned port;
2006
2007	++svm->vcpu.stat.io_exits;
2008	string = (io_info & SVM_IOIO_STR_MASK) != 0;
2009	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
2010	if (string)
2011		return kvm_emulate_instruction(vcpu, 0);
2012
2013	port = io_info >> 16;
2014	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
2015	svm->next_rip = svm->vmcb->control.exit_info_2;
2016
2017	return kvm_fast_pio(&svm->vcpu, size, port, in);
2018}
2019
2020static int nmi_interception(struct vcpu_svm *svm)
2021{
2022	return 1;
2023}
2024
2025static int intr_interception(struct vcpu_svm *svm)
2026{
2027	++svm->vcpu.stat.irq_exits;
2028	return 1;
2029}
2030
2031static int nop_on_interception(struct vcpu_svm *svm)
2032{
2033	return 1;
2034}
2035
2036static int halt_interception(struct vcpu_svm *svm)
2037{
2038	return kvm_emulate_halt(&svm->vcpu);
2039}
2040
2041static int vmmcall_interception(struct vcpu_svm *svm)
2042{
2043	return kvm_emulate_hypercall(&svm->vcpu);
2044}
2045
2046static int vmload_interception(struct vcpu_svm *svm)
2047{
2048	struct vmcb *nested_vmcb;
2049	struct kvm_host_map map;
2050	int ret;
2051
2052	if (nested_svm_check_permissions(svm))
2053		return 1;
2054
2055	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map);
2056	if (ret) {
2057		if (ret == -EINVAL)
2058			kvm_inject_gp(&svm->vcpu, 0);
2059		return 1;
2060	}
2061
2062	nested_vmcb = map.hva;
2063
2064	ret = kvm_skip_emulated_instruction(&svm->vcpu);
2065
2066	nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
2067	kvm_vcpu_unmap(&svm->vcpu, &map, true);
2068
2069	return ret;
2070}
2071
2072static int vmsave_interception(struct vcpu_svm *svm)
2073{
2074	struct vmcb *nested_vmcb;
2075	struct kvm_host_map map;
2076	int ret;
2077
2078	if (nested_svm_check_permissions(svm))
2079		return 1;
2080
2081	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map);
2082	if (ret) {
2083		if (ret == -EINVAL)
2084			kvm_inject_gp(&svm->vcpu, 0);
2085		return 1;
2086	}
2087
2088	nested_vmcb = map.hva;
2089
2090	ret = kvm_skip_emulated_instruction(&svm->vcpu);
2091
2092	nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
2093	kvm_vcpu_unmap(&svm->vcpu, &map, true);
2094
2095	return ret;
2096}
2097
2098static int vmrun_interception(struct vcpu_svm *svm)
2099{
2100	if (nested_svm_check_permissions(svm))
2101		return 1;
2102
2103	return nested_svm_vmrun(svm);
2104}
2105
2106void svm_set_gif(struct vcpu_svm *svm, bool value)
2107{
2108	if (value) {
2109		/*
2110		 * If VGIF is enabled, the STGI intercept is only added to
2111		 * detect the opening of the SMI/NMI window; remove it now.
2112		 * Likewise, clear the VINTR intercept, we will set it
2113		 * again while processing KVM_REQ_EVENT if needed.
2114		 */
2115		if (vgif_enabled(svm))
2116			svm_clr_intercept(svm, INTERCEPT_STGI);
2117		if (svm_is_intercept(svm, INTERCEPT_VINTR))
2118			svm_clear_vintr(svm);
2119
2120		enable_gif(svm);
2121		if (svm->vcpu.arch.smi_pending ||
2122		    svm->vcpu.arch.nmi_pending ||
2123		    kvm_cpu_has_injectable_intr(&svm->vcpu))
2124			kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
2125	} else {
2126		disable_gif(svm);
2127
2128		/*
2129		 * After a CLGI no interrupts should come.  But if vGIF is
2130		 * in use, we still rely on the VINTR intercept (rather than
2131		 * STGI) to detect an open interrupt window.
2132		*/
2133		if (!vgif_enabled(svm))
2134			svm_clear_vintr(svm);
2135	}
2136}
2137
2138static int stgi_interception(struct vcpu_svm *svm)
2139{
2140	int ret;
2141
2142	if (nested_svm_check_permissions(svm))
2143		return 1;
2144
2145	ret = kvm_skip_emulated_instruction(&svm->vcpu);
2146	svm_set_gif(svm, true);
2147	return ret;
2148}
2149
2150static int clgi_interception(struct vcpu_svm *svm)
2151{
2152	int ret;
2153
2154	if (nested_svm_check_permissions(svm))
2155		return 1;
2156
2157	ret = kvm_skip_emulated_instruction(&svm->vcpu);
2158	svm_set_gif(svm, false);
2159	return ret;
2160}
2161
2162static int invlpga_interception(struct vcpu_svm *svm)
2163{
2164	struct kvm_vcpu *vcpu = &svm->vcpu;
2165
2166	trace_kvm_invlpga(svm->vmcb->save.rip, kvm_rcx_read(&svm->vcpu),
2167			  kvm_rax_read(&svm->vcpu));
2168
2169	/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
2170	kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu));
2171
2172	return kvm_skip_emulated_instruction(&svm->vcpu);
2173}
2174
2175static int skinit_interception(struct vcpu_svm *svm)
2176{
2177	trace_kvm_skinit(svm->vmcb->save.rip, kvm_rax_read(&svm->vcpu));
2178
2179	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
2180	return 1;
2181}
2182
2183static int wbinvd_interception(struct vcpu_svm *svm)
2184{
2185	return kvm_emulate_wbinvd(&svm->vcpu);
2186}
2187
2188static int xsetbv_interception(struct vcpu_svm *svm)
2189{
2190	u64 new_bv = kvm_read_edx_eax(&svm->vcpu);
2191	u32 index = kvm_rcx_read(&svm->vcpu);
2192
2193	if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) {
2194		return kvm_skip_emulated_instruction(&svm->vcpu);
2195	}
2196
2197	return 1;
2198}
2199
2200static int rdpru_interception(struct vcpu_svm *svm)
2201{
2202	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
2203	return 1;
2204}
2205
2206static int task_switch_interception(struct vcpu_svm *svm)
2207{
2208	u16 tss_selector;
2209	int reason;
2210	int int_type = svm->vmcb->control.exit_int_info &
2211		SVM_EXITINTINFO_TYPE_MASK;
2212	int int_vec = svm->vmcb->control.exit_int_info & SVM_EVTINJ_VEC_MASK;
2213	uint32_t type =
2214		svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK;
2215	uint32_t idt_v =
2216		svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID;
2217	bool has_error_code = false;
2218	u32 error_code = 0;
2219
2220	tss_selector = (u16)svm->vmcb->control.exit_info_1;
2221
2222	if (svm->vmcb->control.exit_info_2 &
2223	    (1ULL << SVM_EXITINFOSHIFT_TS_REASON_IRET))
2224		reason = TASK_SWITCH_IRET;
2225	else if (svm->vmcb->control.exit_info_2 &
2226		 (1ULL << SVM_EXITINFOSHIFT_TS_REASON_JMP))
2227		reason = TASK_SWITCH_JMP;
2228	else if (idt_v)
2229		reason = TASK_SWITCH_GATE;
2230	else
2231		reason = TASK_SWITCH_CALL;
2232
2233	if (reason == TASK_SWITCH_GATE) {
2234		switch (type) {
2235		case SVM_EXITINTINFO_TYPE_NMI:
2236			svm->vcpu.arch.nmi_injected = false;
2237			break;
2238		case SVM_EXITINTINFO_TYPE_EXEPT:
2239			if (svm->vmcb->control.exit_info_2 &
2240			    (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) {
2241				has_error_code = true;
2242				error_code =
2243					(u32)svm->vmcb->control.exit_info_2;
2244			}
2245			kvm_clear_exception_queue(&svm->vcpu);
2246			break;
2247		case SVM_EXITINTINFO_TYPE_INTR:
2248			kvm_clear_interrupt_queue(&svm->vcpu);
2249			break;
2250		default:
2251			break;
2252		}
2253	}
2254
2255	if (reason != TASK_SWITCH_GATE ||
2256	    int_type == SVM_EXITINTINFO_TYPE_SOFT ||
2257	    (int_type == SVM_EXITINTINFO_TYPE_EXEPT &&
2258	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) {
2259		if (!skip_emulated_instruction(&svm->vcpu))
2260			return 0;
2261	}
2262
2263	if (int_type != SVM_EXITINTINFO_TYPE_SOFT)
2264		int_vec = -1;
2265
2266	return kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason,
2267			       has_error_code, error_code);
2268}
2269
2270static int cpuid_interception(struct vcpu_svm *svm)
2271{
2272	return kvm_emulate_cpuid(&svm->vcpu);
2273}
2274
2275static int iret_interception(struct vcpu_svm *svm)
2276{
2277	++svm->vcpu.stat.nmi_window_exits;
2278	svm_clr_intercept(svm, INTERCEPT_IRET);
2279	svm->vcpu.arch.hflags |= HF_IRET_MASK;
2280	svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu);
2281	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
2282	return 1;
2283}
2284
2285static int invd_interception(struct vcpu_svm *svm)
2286{
2287	/* Treat an INVD instruction as a NOP and just skip it. */
2288	return kvm_skip_emulated_instruction(&svm->vcpu);
2289}
2290
2291static int invlpg_interception(struct vcpu_svm *svm)
2292{
2293	if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
2294		return kvm_emulate_instruction(&svm->vcpu, 0);
2295
2296	kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1);
2297	return kvm_skip_emulated_instruction(&svm->vcpu);
2298}
2299
2300static int emulate_on_interception(struct vcpu_svm *svm)
2301{
2302	return kvm_emulate_instruction(&svm->vcpu, 0);
2303}
2304
2305static int rsm_interception(struct vcpu_svm *svm)
2306{
2307	return kvm_emulate_instruction_from_buffer(&svm->vcpu, rsm_ins_bytes, 2);
2308}
2309
2310static int rdpmc_interception(struct vcpu_svm *svm)
2311{
2312	int err;
2313
2314	if (!nrips)
2315		return emulate_on_interception(svm);
2316
2317	err = kvm_rdpmc(&svm->vcpu);
2318	return kvm_complete_insn_gp(&svm->vcpu, err);
2319}
2320
2321static bool check_selective_cr0_intercepted(struct vcpu_svm *svm,
2322					    unsigned long val)
2323{
2324	unsigned long cr0 = svm->vcpu.arch.cr0;
2325	bool ret = false;
2326
2327	if (!is_guest_mode(&svm->vcpu) ||
2328	    (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))))
2329		return false;
2330
2331	cr0 &= ~SVM_CR0_SELECTIVE_MASK;
2332	val &= ~SVM_CR0_SELECTIVE_MASK;
2333
2334	if (cr0 ^ val) {
2335		svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
2336		ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE);
2337	}
2338
2339	return ret;
2340}
2341
2342#define CR_VALID (1ULL << 63)
2343
2344static int cr_interception(struct vcpu_svm *svm)
2345{
2346	int reg, cr;
2347	unsigned long val;
2348	int err;
2349
2350	if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
2351		return emulate_on_interception(svm);
2352
2353	if (unlikely((svm->vmcb->control.exit_info_1 & CR_VALID) == 0))
2354		return emulate_on_interception(svm);
2355
2356	reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK;
2357	if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE)
2358		cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0;
2359	else
2360		cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0;
2361
2362	err = 0;
2363	if (cr >= 16) { /* mov to cr */
2364		cr -= 16;
2365		val = kvm_register_readl(&svm->vcpu, reg);
2366		trace_kvm_cr_write(cr, val);
2367		switch (cr) {
2368		case 0:
2369			if (!check_selective_cr0_intercepted(svm, val))
2370				err = kvm_set_cr0(&svm->vcpu, val);
2371			else
2372				return 1;
2373
2374			break;
2375		case 3:
2376			err = kvm_set_cr3(&svm->vcpu, val);
2377			break;
2378		case 4:
2379			err = kvm_set_cr4(&svm->vcpu, val);
2380			break;
2381		case 8:
2382			err = kvm_set_cr8(&svm->vcpu, val);
2383			break;
2384		default:
2385			WARN(1, "unhandled write to CR%d", cr);
2386			kvm_queue_exception(&svm->vcpu, UD_VECTOR);
2387			return 1;
2388		}
2389	} else { /* mov from cr */
2390		switch (cr) {
2391		case 0:
2392			val = kvm_read_cr0(&svm->vcpu);
2393			break;
2394		case 2:
2395			val = svm->vcpu.arch.cr2;
2396			break;
2397		case 3:
2398			val = kvm_read_cr3(&svm->vcpu);
2399			break;
2400		case 4:
2401			val = kvm_read_cr4(&svm->vcpu);
2402			break;
2403		case 8:
2404			val = kvm_get_cr8(&svm->vcpu);
2405			break;
2406		default:
2407			WARN(1, "unhandled read from CR%d", cr);
2408			kvm_queue_exception(&svm->vcpu, UD_VECTOR);
2409			return 1;
2410		}
2411		kvm_register_writel(&svm->vcpu, reg, val);
2412		trace_kvm_cr_read(cr, val);
2413	}
2414	return kvm_complete_insn_gp(&svm->vcpu, err);
2415}
2416
2417static int dr_interception(struct vcpu_svm *svm)
2418{
2419	int reg, dr;
2420	unsigned long val;
2421
2422	if (svm->vcpu.guest_debug == 0) {
2423		/*
2424		 * No more DR vmexits; force a reload of the debug registers
2425		 * and reenter on this instruction.  The next vmexit will
2426		 * retrieve the full state of the debug registers.
2427		 */
2428		clr_dr_intercepts(svm);
2429		svm->vcpu.arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT;
2430		return 1;
2431	}
2432
2433	if (!boot_cpu_has(X86_FEATURE_DECODEASSISTS))
2434		return emulate_on_interception(svm);
2435
2436	reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK;
2437	dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0;
2438
2439	if (dr >= 16) { /* mov to DRn */
2440		if (!kvm_require_dr(&svm->vcpu, dr - 16))
2441			return 1;
2442		val = kvm_register_readl(&svm->vcpu, reg);
2443		kvm_set_dr(&svm->vcpu, dr - 16, val);
2444	} else {
2445		if (!kvm_require_dr(&svm->vcpu, dr))
2446			return 1;
2447		kvm_get_dr(&svm->vcpu, dr, &val);
2448		kvm_register_writel(&svm->vcpu, reg, val);
2449	}
2450
2451	return kvm_skip_emulated_instruction(&svm->vcpu);
2452}
2453
2454static int cr8_write_interception(struct vcpu_svm *svm)
2455{
2456	struct kvm_run *kvm_run = svm->vcpu.run;
2457	int r;
2458
2459	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
2460	/* instruction emulation calls kvm_set_cr8() */
2461	r = cr_interception(svm);
2462	if (lapic_in_kernel(&svm->vcpu))
2463		return r;
2464	if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
2465		return r;
2466	kvm_run->exit_reason = KVM_EXIT_SET_TPR;
2467	return 0;
2468}
2469
2470static int svm_get_msr_feature(struct kvm_msr_entry *msr)
2471{
2472	msr->data = 0;
2473
2474	switch (msr->index) {
2475	case MSR_AMD64_DE_CFG:
2476		if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC))
2477			msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE;
2478		break;
2479	case MSR_IA32_PERF_CAPABILITIES:
2480		return 0;
2481	default:
2482		return KVM_MSR_RET_INVALID;
2483	}
2484
2485	return 0;
2486}
2487
2488static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
2489{
2490	struct vcpu_svm *svm = to_svm(vcpu);
2491
2492	switch (msr_info->index) {
2493	case MSR_STAR:
2494		msr_info->data = svm->vmcb->save.star;
2495		break;
2496#ifdef CONFIG_X86_64
2497	case MSR_LSTAR:
2498		msr_info->data = svm->vmcb->save.lstar;
2499		break;
2500	case MSR_CSTAR:
2501		msr_info->data = svm->vmcb->save.cstar;
2502		break;
2503	case MSR_KERNEL_GS_BASE:
2504		msr_info->data = svm->vmcb->save.kernel_gs_base;
2505		break;
2506	case MSR_SYSCALL_MASK:
2507		msr_info->data = svm->vmcb->save.sfmask;
2508		break;
2509#endif
2510	case MSR_IA32_SYSENTER_CS:
2511		msr_info->data = svm->vmcb->save.sysenter_cs;
2512		break;
2513	case MSR_IA32_SYSENTER_EIP:
2514		msr_info->data = svm->sysenter_eip;
2515		break;
2516	case MSR_IA32_SYSENTER_ESP:
2517		msr_info->data = svm->sysenter_esp;
2518		break;
2519	case MSR_TSC_AUX:
2520		if (!boot_cpu_has(X86_FEATURE_RDTSCP))
2521			return 1;
2522		if (!msr_info->host_initiated &&
2523		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
2524			return 1;
2525		msr_info->data = svm->tsc_aux;
2526		break;
2527	/*
2528	 * Nobody will change the following 5 values in the VMCB so we can
2529	 * safely return them on rdmsr. They will always be 0 until LBRV is
2530	 * implemented.
2531	 */
2532	case MSR_IA32_DEBUGCTLMSR:
2533		msr_info->data = svm->vmcb->save.dbgctl;
2534		break;
2535	case MSR_IA32_LASTBRANCHFROMIP:
2536		msr_info->data = svm->vmcb->save.br_from;
2537		break;
2538	case MSR_IA32_LASTBRANCHTOIP:
2539		msr_info->data = svm->vmcb->save.br_to;
2540		break;
2541	case MSR_IA32_LASTINTFROMIP:
2542		msr_info->data = svm->vmcb->save.last_excp_from;
2543		break;
2544	case MSR_IA32_LASTINTTOIP:
2545		msr_info->data = svm->vmcb->save.last_excp_to;
2546		break;
2547	case MSR_VM_HSAVE_PA:
2548		msr_info->data = svm->nested.hsave_msr;
2549		break;
2550	case MSR_VM_CR:
2551		msr_info->data = svm->nested.vm_cr_msr;
2552		break;
2553	case MSR_IA32_SPEC_CTRL:
2554		if (!msr_info->host_initiated &&
2555		    !guest_has_spec_ctrl_msr(vcpu))
2556			return 1;
2557
2558		msr_info->data = svm->spec_ctrl;
2559		break;
2560	case MSR_AMD64_VIRT_SPEC_CTRL:
2561		if (!msr_info->host_initiated &&
2562		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
2563			return 1;
2564
2565		msr_info->data = svm->virt_spec_ctrl;
2566		break;
2567	case MSR_F15H_IC_CFG: {
2568
2569		int family, model;
2570
2571		family = guest_cpuid_family(vcpu);
2572		model  = guest_cpuid_model(vcpu);
2573
2574		if (family < 0 || model < 0)
2575			return kvm_get_msr_common(vcpu, msr_info);
2576
2577		msr_info->data = 0;
2578
2579		if (family == 0x15 &&
2580		    (model >= 0x2 && model < 0x20))
2581			msr_info->data = 0x1E;
2582		}
2583		break;
2584	case MSR_AMD64_DE_CFG:
2585		msr_info->data = svm->msr_decfg;
2586		break;
2587	default:
2588		return kvm_get_msr_common(vcpu, msr_info);
2589	}
2590	return 0;
2591}
2592
2593static int rdmsr_interception(struct vcpu_svm *svm)
2594{
2595	return kvm_emulate_rdmsr(&svm->vcpu);
2596}
2597
2598static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
2599{
2600	struct vcpu_svm *svm = to_svm(vcpu);
2601	int svm_dis, chg_mask;
2602
2603	if (data & ~SVM_VM_CR_VALID_MASK)
2604		return 1;
2605
2606	chg_mask = SVM_VM_CR_VALID_MASK;
2607
2608	if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK)
2609		chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK);
2610
2611	svm->nested.vm_cr_msr &= ~chg_mask;
2612	svm->nested.vm_cr_msr |= (data & chg_mask);
2613
2614	svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK;
2615
2616	/* check for svm_disable while efer.svme is set */
2617	if (svm_dis && (vcpu->arch.efer & EFER_SVME))
2618		return 1;
2619
2620	return 0;
2621}
2622
2623static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
2624{
2625	struct vcpu_svm *svm = to_svm(vcpu);
2626
2627	u32 ecx = msr->index;
2628	u64 data = msr->data;
2629	switch (ecx) {
2630	case MSR_IA32_CR_PAT:
2631		if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
2632			return 1;
2633		vcpu->arch.pat = data;
2634		svm->vmcb->save.g_pat = data;
2635		vmcb_mark_dirty(svm->vmcb, VMCB_NPT);
2636		break;
2637	case MSR_IA32_SPEC_CTRL:
2638		if (!msr->host_initiated &&
2639		    !guest_has_spec_ctrl_msr(vcpu))
2640			return 1;
2641
2642		if (kvm_spec_ctrl_test_value(data))
2643			return 1;
2644
2645		svm->spec_ctrl = data;
2646		if (!data)
2647			break;
2648
2649		/*
2650		 * For non-nested:
2651		 * When it's written (to non-zero) for the first time, pass
2652		 * it through.
2653		 *
2654		 * For nested:
2655		 * The handling of the MSR bitmap for L2 guests is done in
2656		 * nested_svm_vmrun_msrpm.
2657		 * We update the L1 MSR bit as well since it will end up
2658		 * touching the MSR anyway now.
2659		 */
2660		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
2661		break;
2662	case MSR_IA32_PRED_CMD:
2663		if (!msr->host_initiated &&
2664		    !guest_has_pred_cmd_msr(vcpu))
2665			return 1;
2666
2667		if (data & ~PRED_CMD_IBPB)
2668			return 1;
2669		if (!boot_cpu_has(X86_FEATURE_IBPB))
2670			return 1;
2671		if (!data)
2672			break;
2673
2674		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
2675		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
2676		break;
2677	case MSR_AMD64_VIRT_SPEC_CTRL:
2678		if (!msr->host_initiated &&
2679		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
2680			return 1;
2681
2682		if (data & ~SPEC_CTRL_SSBD)
2683			return 1;
2684
2685		svm->virt_spec_ctrl = data;
2686		break;
2687	case MSR_STAR:
2688		svm->vmcb->save.star = data;
2689		break;
2690#ifdef CONFIG_X86_64
2691	case MSR_LSTAR:
2692		svm->vmcb->save.lstar = data;
2693		break;
2694	case MSR_CSTAR:
2695		svm->vmcb->save.cstar = data;
2696		break;
2697	case MSR_KERNEL_GS_BASE:
2698		svm->vmcb->save.kernel_gs_base = data;
2699		break;
2700	case MSR_SYSCALL_MASK:
2701		svm->vmcb->save.sfmask = data;
2702		break;
2703#endif
2704	case MSR_IA32_SYSENTER_CS:
2705		svm->vmcb->save.sysenter_cs = data;
2706		break;
2707	case MSR_IA32_SYSENTER_EIP:
2708		svm->sysenter_eip = data;
2709		svm->vmcb->save.sysenter_eip = data;
2710		break;
2711	case MSR_IA32_SYSENTER_ESP:
2712		svm->sysenter_esp = data;
2713		svm->vmcb->save.sysenter_esp = data;
2714		break;
2715	case MSR_TSC_AUX:
2716		if (!boot_cpu_has(X86_FEATURE_RDTSCP))
2717			return 1;
2718
2719		if (!msr->host_initiated &&
2720		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
2721			return 1;
2722
2723		/*
2724		 * This is rare, so we update the MSR here instead of using
2725		 * direct_access_msrs.  Doing that would require a rdmsr in
2726		 * svm_vcpu_put.
2727		 */
2728		svm->tsc_aux = data;
2729		wrmsrl(MSR_TSC_AUX, svm->tsc_aux);
2730		break;
2731	case MSR_IA32_DEBUGCTLMSR:
2732		if (!boot_cpu_has(X86_FEATURE_LBRV)) {
2733			vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n",
2734				    __func__, data);
2735			break;
2736		}
2737		if (data & DEBUGCTL_RESERVED_BITS)
2738			return 1;
2739
2740		svm->vmcb->save.dbgctl = data;
2741		vmcb_mark_dirty(svm->vmcb, VMCB_LBR);
2742		if (data & (1ULL<<0))
2743			svm_enable_lbrv(vcpu);
2744		else
2745			svm_disable_lbrv(vcpu);
2746		break;
2747	case MSR_VM_HSAVE_PA:
2748		/*
2749		 * Old kernels did not validate the value written to
2750		 * MSR_VM_HSAVE_PA.  Allow KVM_SET_MSR to set an invalid
2751		 * value to allow live migrating buggy or malicious guests
2752		 * originating from those kernels.
2753		 */
2754		if (!msr->host_initiated && !page_address_valid(vcpu, data))
2755			return 1;
2756
2757		svm->nested.hsave_msr = data & PAGE_MASK;
2758		break;
2759	case MSR_VM_CR:
2760		return svm_set_vm_cr(vcpu, data);
2761	case MSR_VM_IGNNE:
2762		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
2763		break;
2764	case MSR_AMD64_DE_CFG: {
2765		struct kvm_msr_entry msr_entry;
2766
2767		msr_entry.index = msr->index;
2768		if (svm_get_msr_feature(&msr_entry))
2769			return 1;
2770
2771		/* Check the supported bits */
2772		if (data & ~msr_entry.data)
2773			return 1;
2774
2775		/* Don't allow the guest to change a bit, #GP */
2776		if (!msr->host_initiated && (data ^ msr_entry.data))
2777			return 1;
2778
2779		svm->msr_decfg = data;
2780		break;
2781	}
2782	case MSR_IA32_APICBASE:
2783		if (kvm_vcpu_apicv_active(vcpu))
2784			avic_update_vapic_bar(to_svm(vcpu), data);
2785		fallthrough;
2786	default:
2787		return kvm_set_msr_common(vcpu, msr);
2788	}
2789	return 0;
2790}
2791
2792static int wrmsr_interception(struct vcpu_svm *svm)
2793{
2794	return kvm_emulate_wrmsr(&svm->vcpu);
2795}
2796
2797static int msr_interception(struct vcpu_svm *svm)
2798{
2799	if (svm->vmcb->control.exit_info_1)
2800		return wrmsr_interception(svm);
2801	else
2802		return rdmsr_interception(svm);
2803}
2804
2805static int interrupt_window_interception(struct vcpu_svm *svm)
2806{
2807	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
2808	svm_clear_vintr(svm);
2809
2810	/*
2811	 * For AVIC, the only reason to end up here is ExtINTs.
2812	 * In this case AVIC was temporarily disabled for
2813	 * requesting the IRQ window and we have to re-enable it.
2814	 */
2815	svm_toggle_avic_for_irq_window(&svm->vcpu, true);
2816
2817	++svm->vcpu.stat.irq_window_exits;
2818	return 1;
2819}
2820
2821static int pause_interception(struct vcpu_svm *svm)
2822{
2823	struct kvm_vcpu *vcpu = &svm->vcpu;
2824	bool in_kernel = (svm_get_cpl(vcpu) == 0);
2825
2826	if (!kvm_pause_in_guest(vcpu->kvm))
2827		grow_ple_window(vcpu);
2828
2829	kvm_vcpu_on_spin(vcpu, in_kernel);
2830	return 1;
2831}
2832
2833static int nop_interception(struct vcpu_svm *svm)
2834{
2835	return kvm_skip_emulated_instruction(&(svm->vcpu));
2836}
2837
2838static int monitor_interception(struct vcpu_svm *svm)
2839{
2840	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
2841	return nop_interception(svm);
2842}
2843
2844static int mwait_interception(struct vcpu_svm *svm)
2845{
2846	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
2847	return nop_interception(svm);
2848}
2849
2850static int invpcid_interception(struct vcpu_svm *svm)
2851{
2852	struct kvm_vcpu *vcpu = &svm->vcpu;
2853	unsigned long type;
2854	gva_t gva;
2855
2856	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
2857		kvm_queue_exception(vcpu, UD_VECTOR);
2858		return 1;
2859	}
2860
2861	/*
2862	 * For an INVPCID intercept:
2863	 * EXITINFO1 provides the linear address of the memory operand.
2864	 * EXITINFO2 provides the contents of the register operand.
2865	 */
2866	type = svm->vmcb->control.exit_info_2;
2867	gva = svm->vmcb->control.exit_info_1;
2868
2869	if (type > 3) {
2870		kvm_inject_gp(vcpu, 0);
2871		return 1;
2872	}
2873
2874	return kvm_handle_invpcid(vcpu, type, gva);
2875}
2876
2877static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
2878	[SVM_EXIT_READ_CR0]			= cr_interception,
2879	[SVM_EXIT_READ_CR3]			= cr_interception,
2880	[SVM_EXIT_READ_CR4]			= cr_interception,
2881	[SVM_EXIT_READ_CR8]			= cr_interception,
2882	[SVM_EXIT_CR0_SEL_WRITE]		= cr_interception,
2883	[SVM_EXIT_WRITE_CR0]			= cr_interception,
2884	[SVM_EXIT_WRITE_CR3]			= cr_interception,
2885	[SVM_EXIT_WRITE_CR4]			= cr_interception,
2886	[SVM_EXIT_WRITE_CR8]			= cr8_write_interception,
2887	[SVM_EXIT_READ_DR0]			= dr_interception,
2888	[SVM_EXIT_READ_DR1]			= dr_interception,
2889	[SVM_EXIT_READ_DR2]			= dr_interception,
2890	[SVM_EXIT_READ_DR3]			= dr_interception,
2891	[SVM_EXIT_READ_DR4]			= dr_interception,
2892	[SVM_EXIT_READ_DR5]			= dr_interception,
2893	[SVM_EXIT_READ_DR6]			= dr_interception,
2894	[SVM_EXIT_READ_DR7]			= dr_interception,
2895	[SVM_EXIT_WRITE_DR0]			= dr_interception,
2896	[SVM_EXIT_WRITE_DR1]			= dr_interception,
2897	[SVM_EXIT_WRITE_DR2]			= dr_interception,
2898	[SVM_EXIT_WRITE_DR3]			= dr_interception,
2899	[SVM_EXIT_WRITE_DR4]			= dr_interception,
2900	[SVM_EXIT_WRITE_DR5]			= dr_interception,
2901	[SVM_EXIT_WRITE_DR6]			= dr_interception,
2902	[SVM_EXIT_WRITE_DR7]			= dr_interception,
2903	[SVM_EXIT_EXCP_BASE + DB_VECTOR]	= db_interception,
2904	[SVM_EXIT_EXCP_BASE + BP_VECTOR]	= bp_interception,
2905	[SVM_EXIT_EXCP_BASE + UD_VECTOR]	= ud_interception,
2906	[SVM_EXIT_EXCP_BASE + PF_VECTOR]	= pf_interception,
2907	[SVM_EXIT_EXCP_BASE + MC_VECTOR]	= mc_interception,
2908	[SVM_EXIT_EXCP_BASE + AC_VECTOR]	= ac_interception,
2909	[SVM_EXIT_EXCP_BASE + GP_VECTOR]	= gp_interception,
2910	[SVM_EXIT_INTR]				= intr_interception,
2911	[SVM_EXIT_NMI]				= nmi_interception,
2912	[SVM_EXIT_SMI]				= nop_on_interception,
2913	[SVM_EXIT_INIT]				= nop_on_interception,
2914	[SVM_EXIT_VINTR]			= interrupt_window_interception,
2915	[SVM_EXIT_RDPMC]			= rdpmc_interception,
2916	[SVM_EXIT_CPUID]			= cpuid_interception,
2917	[SVM_EXIT_IRET]                         = iret_interception,
2918	[SVM_EXIT_INVD]                         = invd_interception,
2919	[SVM_EXIT_PAUSE]			= pause_interception,
2920	[SVM_EXIT_HLT]				= halt_interception,
2921	[SVM_EXIT_INVLPG]			= invlpg_interception,
2922	[SVM_EXIT_INVLPGA]			= invlpga_interception,
2923	[SVM_EXIT_IOIO]				= io_interception,
2924	[SVM_EXIT_MSR]				= msr_interception,
2925	[SVM_EXIT_TASK_SWITCH]			= task_switch_interception,
2926	[SVM_EXIT_SHUTDOWN]			= shutdown_interception,
2927	[SVM_EXIT_VMRUN]			= vmrun_interception,
2928	[SVM_EXIT_VMMCALL]			= vmmcall_interception,
2929	[SVM_EXIT_VMLOAD]			= vmload_interception,
2930	[SVM_EXIT_VMSAVE]			= vmsave_interception,
2931	[SVM_EXIT_STGI]				= stgi_interception,
2932	[SVM_EXIT_CLGI]				= clgi_interception,
2933	[SVM_EXIT_SKINIT]			= skinit_interception,
2934	[SVM_EXIT_WBINVD]                       = wbinvd_interception,
2935	[SVM_EXIT_MONITOR]			= monitor_interception,
2936	[SVM_EXIT_MWAIT]			= mwait_interception,
2937	[SVM_EXIT_XSETBV]			= xsetbv_interception,
2938	[SVM_EXIT_RDPRU]			= rdpru_interception,
2939	[SVM_EXIT_INVPCID]                      = invpcid_interception,
2940	[SVM_EXIT_NPF]				= npf_interception,
2941	[SVM_EXIT_RSM]                          = rsm_interception,
2942	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
2943	[SVM_EXIT_AVIC_UNACCELERATED_ACCESS]	= avic_unaccelerated_access_interception,
2944};
2945
2946static void dump_vmcb(struct kvm_vcpu *vcpu)
2947{
2948	struct vcpu_svm *svm = to_svm(vcpu);
2949	struct vmcb_control_area *control = &svm->vmcb->control;
2950	struct vmcb_save_area *save = &svm->vmcb->save;
2951
2952	if (!dump_invalid_vmcb) {
2953		pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
2954		return;
2955	}
2956
2957	pr_err("VMCB Control Area:\n");
2958	pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff);
2959	pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16);
2960	pr_err("%-20s%04x\n", "dr_read:", control->intercepts[INTERCEPT_DR] & 0xffff);
2961	pr_err("%-20s%04x\n", "dr_write:", control->intercepts[INTERCEPT_DR] >> 16);
2962	pr_err("%-20s%08x\n", "exceptions:", control->intercepts[INTERCEPT_EXCEPTION]);
2963	pr_err("%-20s%08x %08x\n", "intercepts:",
2964              control->intercepts[INTERCEPT_WORD3],
2965	       control->intercepts[INTERCEPT_WORD4]);
2966	pr_err("%-20s%d\n", "pause filter count:", control->pause_filter_count);
2967	pr_err("%-20s%d\n", "pause filter threshold:",
2968	       control->pause_filter_thresh);
2969	pr_err("%-20s%016llx\n", "iopm_base_pa:", control->iopm_base_pa);
2970	pr_err("%-20s%016llx\n", "msrpm_base_pa:", control->msrpm_base_pa);
2971	pr_err("%-20s%016llx\n", "tsc_offset:", control->tsc_offset);
2972	pr_err("%-20s%d\n", "asid:", control->asid);
2973	pr_err("%-20s%d\n", "tlb_ctl:", control->tlb_ctl);
2974	pr_err("%-20s%08x\n", "int_ctl:", control->int_ctl);
2975	pr_err("%-20s%08x\n", "int_vector:", control->int_vector);
2976	pr_err("%-20s%08x\n", "int_state:", control->int_state);
2977	pr_err("%-20s%08x\n", "exit_code:", control->exit_code);
2978	pr_err("%-20s%016llx\n", "exit_info1:", control->exit_info_1);
2979	pr_err("%-20s%016llx\n", "exit_info2:", control->exit_info_2);
2980	pr_err("%-20s%08x\n", "exit_int_info:", control->exit_int_info);
2981	pr_err("%-20s%08x\n", "exit_int_info_err:", control->exit_int_info_err);
2982	pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl);
2983	pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3);
2984	pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar);
2985	pr_err("%-20s%08x\n", "event_inj:", control->event_inj);
2986	pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err);
2987	pr_err("%-20s%lld\n", "virt_ext:", control->virt_ext);
2988	pr_err("%-20s%016llx\n", "next_rip:", control->next_rip);
2989	pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page);
2990	pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id);
2991	pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id);
2992	pr_err("VMCB State Save Area:\n");
2993	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
2994	       "es:",
2995	       save->es.selector, save->es.attrib,
2996	       save->es.limit, save->es.base);
2997	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
2998	       "cs:",
2999	       save->cs.selector, save->cs.attrib,
3000	       save->cs.limit, save->cs.base);
3001	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
3002	       "ss:",
3003	       save->ss.selector, save->ss.attrib,
3004	       save->ss.limit, save->ss.base);
3005	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
3006	       "ds:",
3007	       save->ds.selector, save->ds.attrib,
3008	       save->ds.limit, save->ds.base);
3009	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
3010	       "fs:",
3011	       save->fs.selector, save->fs.attrib,
3012	       save->fs.limit, save->fs.base);
3013	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
3014	       "gs:",
3015	       save->gs.selector, save->gs.attrib,
3016	       save->gs.limit, save->gs.base);
3017	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
3018	       "gdtr:",
3019	       save->gdtr.selector, save->gdtr.attrib,
3020	       save->gdtr.limit, save->gdtr.base);
3021	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
3022	       "ldtr:",
3023	       save->ldtr.selector, save->ldtr.attrib,
3024	       save->ldtr.limit, save->ldtr.base);
3025	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
3026	       "idtr:",
3027	       save->idtr.selector, save->idtr.attrib,
3028	       save->idtr.limit, save->idtr.base);
3029	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
3030	       "tr:",
3031	       save->tr.selector, save->tr.attrib,
3032	       save->tr.limit, save->tr.base);
3033	pr_err("cpl:            %d                efer:         %016llx\n",
3034		save->cpl, save->efer);
3035	pr_err("%-15s %016llx %-13s %016llx\n",
3036	       "cr0:", save->cr0, "cr2:", save->cr2);
3037	pr_err("%-15s %016llx %-13s %016llx\n",
3038	       "cr3:", save->cr3, "cr4:", save->cr4);
3039	pr_err("%-15s %016llx %-13s %016llx\n",
3040	       "dr6:", save->dr6, "dr7:", save->dr7);
3041	pr_err("%-15s %016llx %-13s %016llx\n",
3042	       "rip:", save->rip, "rflags:", save->rflags);
3043	pr_err("%-15s %016llx %-13s %016llx\n",
3044	       "rsp:", save->rsp, "rax:", save->rax);
3045	pr_err("%-15s %016llx %-13s %016llx\n",
3046	       "star:", save->star, "lstar:", save->lstar);
3047	pr_err("%-15s %016llx %-13s %016llx\n",
3048	       "cstar:", save->cstar, "sfmask:", save->sfmask);
3049	pr_err("%-15s %016llx %-13s %016llx\n",
3050	       "kernel_gs_base:", save->kernel_gs_base,
3051	       "sysenter_cs:", save->sysenter_cs);
3052	pr_err("%-15s %016llx %-13s %016llx\n",
3053	       "sysenter_esp:", save->sysenter_esp,
3054	       "sysenter_eip:", save->sysenter_eip);
3055	pr_err("%-15s %016llx %-13s %016llx\n",
3056	       "gpat:", save->g_pat, "dbgctl:", save->dbgctl);
3057	pr_err("%-15s %016llx %-13s %016llx\n",
3058	       "br_from:", save->br_from, "br_to:", save->br_to);
3059	pr_err("%-15s %016llx %-13s %016llx\n",
3060	       "excp_from:", save->last_excp_from,
3061	       "excp_to:", save->last_excp_to);
3062}
3063
3064static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2,
3065			      u32 *intr_info, u32 *error_code)
3066{
3067	struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control;
3068
3069	*info1 = control->exit_info_1;
3070	*info2 = control->exit_info_2;
3071	*intr_info = control->exit_int_info;
3072	if ((*intr_info & SVM_EXITINTINFO_VALID) &&
3073	    (*intr_info & SVM_EXITINTINFO_VALID_ERR))
3074		*error_code = control->exit_int_info_err;
3075	else
3076		*error_code = 0;
3077}
3078
3079static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
3080{
3081	struct vcpu_svm *svm = to_svm(vcpu);
3082	struct kvm_run *kvm_run = vcpu->run;
3083	u32 exit_code = svm->vmcb->control.exit_code;
3084
3085	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
3086
3087	if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE))
3088		vcpu->arch.cr0 = svm->vmcb->save.cr0;
3089	if (npt_enabled)
3090		vcpu->arch.cr3 = svm->vmcb->save.cr3;
3091
3092	if (is_guest_mode(vcpu)) {
3093		int vmexit;
3094
3095		trace_kvm_nested_vmexit(exit_code, vcpu, KVM_ISA_SVM);
3096
3097		vmexit = nested_svm_exit_special(svm);
3098
3099		if (vmexit == NESTED_EXIT_CONTINUE)
3100			vmexit = nested_svm_exit_handled(svm);
3101
3102		if (vmexit == NESTED_EXIT_DONE)
3103			return 1;
3104	}
3105
3106	if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
3107		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
3108		kvm_run->fail_entry.hardware_entry_failure_reason
3109			= svm->vmcb->control.exit_code;
3110		kvm_run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu;
3111		dump_vmcb(vcpu);
3112		return 0;
3113	}
3114
3115	if (exit_fastpath != EXIT_FASTPATH_NONE)
3116		return 1;
3117
3118	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
3119	    || !svm_exit_handlers[exit_code]) {
3120		vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code);
3121		dump_vmcb(vcpu);
3122		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
3123		vcpu->run->internal.suberror =
3124			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
3125		vcpu->run->internal.ndata = 2;
3126		vcpu->run->internal.data[0] = exit_code;
3127		vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
3128		return 0;
3129	}
3130
3131#ifdef CONFIG_RETPOLINE
3132	if (exit_code == SVM_EXIT_MSR)
3133		return msr_interception(svm);
3134	else if (exit_code == SVM_EXIT_VINTR)
3135		return interrupt_window_interception(svm);
3136	else if (exit_code == SVM_EXIT_INTR)
3137		return intr_interception(svm);
3138	else if (exit_code == SVM_EXIT_HLT)
3139		return halt_interception(svm);
3140	else if (exit_code == SVM_EXIT_NPF)
3141		return npf_interception(svm);
3142#endif
3143	return svm_exit_handlers[exit_code](svm);
3144}
3145
3146static void reload_tss(struct kvm_vcpu *vcpu)
3147{
3148	struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
3149
3150	sd->tss_desc->type = 9; /* available 32/64-bit TSS */
3151	load_TR_desc();
3152}
3153
3154static void pre_svm_run(struct vcpu_svm *svm)
3155{
3156	struct svm_cpu_data *sd = per_cpu(svm_data, svm->vcpu.cpu);
3157
3158	if (sev_guest(svm->vcpu.kvm))
3159		return pre_sev_run(svm, svm->vcpu.cpu);
3160
3161	/* FIXME: handle wraparound of asid_generation */
3162	if (svm->asid_generation != sd->asid_generation)
3163		new_asid(svm, sd);
3164}
3165
3166static void svm_inject_nmi(struct kvm_vcpu *vcpu)
3167{
3168	struct vcpu_svm *svm = to_svm(vcpu);
3169
3170	svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
3171	vcpu->arch.hflags |= HF_NMI_MASK;
3172	svm_set_intercept(svm, INTERCEPT_IRET);
3173	++vcpu->stat.nmi_injections;
3174}
3175
3176static void svm_set_irq(struct kvm_vcpu *vcpu)
3177{
3178	struct vcpu_svm *svm = to_svm(vcpu);
3179
3180	trace_kvm_inj_virq(vcpu->arch.interrupt.nr);
3181	++vcpu->stat.irq_injections;
3182
3183	svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr |
3184		SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
3185}
3186
3187static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
3188{
3189	struct vcpu_svm *svm = to_svm(vcpu);
3190
3191	if (nested_svm_virtualize_tpr(vcpu))
3192		return;
3193
3194	svm_clr_intercept(svm, INTERCEPT_CR8_WRITE);
3195
3196	if (irr == -1)
3197		return;
3198
3199	if (tpr >= irr)
3200		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
3201}
3202
3203bool svm_nmi_blocked(struct kvm_vcpu *vcpu)
3204{
3205	struct vcpu_svm *svm = to_svm(vcpu);
3206	struct vmcb *vmcb = svm->vmcb;
3207	bool ret;
3208
3209	if (!gif_set(svm))
3210		return true;
3211
3212	if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm))
3213		return false;
3214
3215	ret = (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) ||
3216	      (svm->vcpu.arch.hflags & HF_NMI_MASK);
3217
3218	return ret;
3219}
3220
3221static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
3222{
3223	struct vcpu_svm *svm = to_svm(vcpu);
3224	if (svm->nested.nested_run_pending)
3225		return -EBUSY;
3226
3227	/* An NMI must not be injected into L2 if it's supposed to VM-Exit.  */
3228	if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(svm))
3229		return -EBUSY;
3230
3231	return !svm_nmi_blocked(vcpu);
3232}
3233
3234static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
3235{
3236	struct vcpu_svm *svm = to_svm(vcpu);
3237
3238	return !!(svm->vcpu.arch.hflags & HF_NMI_MASK);
3239}
3240
3241static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
3242{
3243	struct vcpu_svm *svm = to_svm(vcpu);
3244
3245	if (masked) {
3246		svm->vcpu.arch.hflags |= HF_NMI_MASK;
3247		svm_set_intercept(svm, INTERCEPT_IRET);
3248	} else {
3249		svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
3250		svm_clr_intercept(svm, INTERCEPT_IRET);
3251	}
3252}
3253
3254bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
3255{
3256	struct vcpu_svm *svm = to_svm(vcpu);
3257	struct vmcb *vmcb = svm->vmcb;
3258
3259	if (!gif_set(svm))
3260		return true;
3261
3262	if (is_guest_mode(vcpu)) {
3263		/* As long as interrupts are being delivered...  */
3264		if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK)
3265		    ? !(svm->nested.hsave->save.rflags & X86_EFLAGS_IF)
3266		    : !(kvm_get_rflags(vcpu) & X86_EFLAGS_IF))
3267			return true;
3268
3269		/* ... vmexits aren't blocked by the interrupt shadow  */
3270		if (nested_exit_on_intr(svm))
3271			return false;
3272	} else {
3273		if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF))
3274			return true;
3275	}
3276
3277	return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK);
3278}
3279
3280static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
3281{
3282	struct vcpu_svm *svm = to_svm(vcpu);
3283	if (svm->nested.nested_run_pending)
3284		return -EBUSY;
3285
3286	/*
3287	 * An IRQ must not be injected into L2 if it's supposed to VM-Exit,
3288	 * e.g. if the IRQ arrived asynchronously after checking nested events.
3289	 */
3290	if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm))
3291		return -EBUSY;
3292
3293	return !svm_interrupt_blocked(vcpu);
3294}
3295
3296static void enable_irq_window(struct kvm_vcpu *vcpu)
3297{
3298	struct vcpu_svm *svm = to_svm(vcpu);
3299
3300	/*
3301	 * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
3302	 * 1, because that's a separate STGI/VMRUN intercept.  The next time we
3303	 * get that intercept, this function will be called again though and
3304	 * we'll get the vintr intercept. However, if the vGIF feature is
3305	 * enabled, the STGI interception will not occur. Enable the irq
3306	 * window under the assumption that the hardware will set the GIF.
3307	 */
3308	if (vgif_enabled(svm) || gif_set(svm)) {
3309		/*
3310		 * IRQ window is not needed when AVIC is enabled,
3311		 * unless we have pending ExtINT since it cannot be injected
3312		 * via AVIC. In such case, we need to temporarily disable AVIC,
3313		 * and fallback to injecting IRQ via V_IRQ.
3314		 */
3315		svm_toggle_avic_for_irq_window(vcpu, false);
3316		svm_set_vintr(svm);
3317	}
3318}
3319
3320static void enable_nmi_window(struct kvm_vcpu *vcpu)
3321{
3322	struct vcpu_svm *svm = to_svm(vcpu);
3323
3324	if ((svm->vcpu.arch.hflags & (HF_NMI_MASK | HF_IRET_MASK))
3325	    == HF_NMI_MASK)
3326		return; /* IRET will cause a vm exit */
3327
3328	if (!gif_set(svm)) {
3329		if (vgif_enabled(svm))
3330			svm_set_intercept(svm, INTERCEPT_STGI);
3331		return; /* STGI will cause a vm exit */
3332	}
3333
3334	/*
3335	 * Something prevents NMI from been injected. Single step over possible
3336	 * problem (IRET or exception injection or interrupt shadow)
3337	 */
3338	svm->nmi_singlestep_guest_rflags = svm_get_rflags(vcpu);
3339	svm->nmi_singlestep = true;
3340	svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
3341}
3342
3343static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
3344{
3345	return 0;
3346}
3347
3348static int svm_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
3349{
3350	return 0;
3351}
3352
3353void svm_flush_tlb(struct kvm_vcpu *vcpu)
3354{
3355	struct vcpu_svm *svm = to_svm(vcpu);
3356
3357	/*
3358	 * Flush only the current ASID even if the TLB flush was invoked via
3359	 * kvm_flush_remote_tlbs().  Although flushing remote TLBs requires all
3360	 * ASIDs to be flushed, KVM uses a single ASID for L1 and L2, and
3361	 * unconditionally does a TLB flush on both nested VM-Enter and nested
3362	 * VM-Exit (via kvm_mmu_reset_context()).
3363	 */
3364	if (static_cpu_has(X86_FEATURE_FLUSHBYASID))
3365		svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
3366	else
3367		svm->asid_generation--;
3368}
3369
3370static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva)
3371{
3372	struct vcpu_svm *svm = to_svm(vcpu);
3373
3374	invlpga(gva, svm->vmcb->control.asid);
3375}
3376
3377static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
3378{
3379	amd_clear_divider();
3380}
3381
3382static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
3383{
3384	struct vcpu_svm *svm = to_svm(vcpu);
3385
3386	if (nested_svm_virtualize_tpr(vcpu))
3387		return;
3388
3389	if (!svm_is_intercept(svm, INTERCEPT_CR8_WRITE)) {
3390		int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
3391		kvm_set_cr8(vcpu, cr8);
3392	}
3393}
3394
3395static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
3396{
3397	struct vcpu_svm *svm = to_svm(vcpu);
3398	u64 cr8;
3399
3400	if (nested_svm_virtualize_tpr(vcpu) ||
3401	    kvm_vcpu_apicv_active(vcpu))
3402		return;
3403
3404	cr8 = kvm_get_cr8(vcpu);
3405	svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
3406	svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
3407}
3408
3409static void svm_complete_interrupts(struct vcpu_svm *svm)
3410{
3411	u8 vector;
3412	int type;
3413	u32 exitintinfo = svm->vmcb->control.exit_int_info;
3414	unsigned int3_injected = svm->int3_injected;
3415
3416	svm->int3_injected = 0;
3417
3418	/*
3419	 * If we've made progress since setting HF_IRET_MASK, we've
3420	 * executed an IRET and can allow NMI injection.
3421	 */
3422	if ((svm->vcpu.arch.hflags & HF_IRET_MASK)
3423	    && kvm_rip_read(&svm->vcpu) != svm->nmi_iret_rip) {
3424		svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
3425		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
3426	}
3427
3428	svm->vcpu.arch.nmi_injected = false;
3429	kvm_clear_exception_queue(&svm->vcpu);
3430	kvm_clear_interrupt_queue(&svm->vcpu);
3431
3432	if (!(exitintinfo & SVM_EXITINTINFO_VALID))
3433		return;
3434
3435	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
3436
3437	vector = exitintinfo & SVM_EXITINTINFO_VEC_MASK;
3438	type = exitintinfo & SVM_EXITINTINFO_TYPE_MASK;
3439
3440	switch (type) {
3441	case SVM_EXITINTINFO_TYPE_NMI:
3442		svm->vcpu.arch.nmi_injected = true;
3443		break;
3444	case SVM_EXITINTINFO_TYPE_EXEPT:
3445		/*
3446		 * In case of software exceptions, do not reinject the vector,
3447		 * but re-execute the instruction instead. Rewind RIP first
3448		 * if we emulated INT3 before.
3449		 */
3450		if (kvm_exception_is_soft(vector)) {
3451			if (vector == BP_VECTOR && int3_injected &&
3452			    kvm_is_linear_rip(&svm->vcpu, svm->int3_rip))
3453				kvm_rip_write(&svm->vcpu,
3454					      kvm_rip_read(&svm->vcpu) -
3455					      int3_injected);
3456			break;
3457		}
3458		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
3459			u32 err = svm->vmcb->control.exit_int_info_err;
3460			kvm_requeue_exception_e(&svm->vcpu, vector, err);
3461
3462		} else
3463			kvm_requeue_exception(&svm->vcpu, vector);
3464		break;
3465	case SVM_EXITINTINFO_TYPE_INTR:
3466		kvm_queue_interrupt(&svm->vcpu, vector, false);
3467		break;
3468	default:
3469		break;
3470	}
3471}
3472
3473static void svm_cancel_injection(struct kvm_vcpu *vcpu)
3474{
3475	struct vcpu_svm *svm = to_svm(vcpu);
3476	struct vmcb_control_area *control = &svm->vmcb->control;
3477
3478	control->exit_int_info = control->event_inj;
3479	control->exit_int_info_err = control->event_inj_err;
3480	control->event_inj = 0;
3481	svm_complete_interrupts(svm);
3482}
3483
3484static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
3485{
3486	struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control;
3487
3488	/*
3489	 * Note, the next RIP must be provided as SRCU isn't held, i.e. KVM
3490	 * can't read guest memory (dereference memslots) to decode the WRMSR.
3491	 */
3492	if (control->exit_code == SVM_EXIT_MSR && control->exit_info_1 &&
3493	    nrips && control->next_rip)
3494		return handle_fastpath_set_msr_irqoff(vcpu);
3495
3496	return EXIT_FASTPATH_NONE;
3497}
3498
3499void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
3500
3501static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
3502					struct vcpu_svm *svm)
3503{
3504	/*
3505	 * VMENTER enables interrupts (host state), but the kernel state is
3506	 * interrupts disabled when this is invoked. Also tell RCU about
3507	 * it. This is the same logic as for exit_to_user_mode().
3508	 *
3509	 * This ensures that e.g. latency analysis on the host observes
3510	 * guest mode as interrupt enabled.
3511	 *
3512	 * guest_enter_irqoff() informs context tracking about the
3513	 * transition to guest mode and if enabled adjusts RCU state
3514	 * accordingly.
3515	 */
3516	instrumentation_begin();
3517	trace_hardirqs_on_prepare();
3518	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
3519	instrumentation_end();
3520
3521	guest_enter_irqoff();
3522	lockdep_hardirqs_on(CALLER_ADDR0);
3523
3524	__svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs);
3525
3526#ifdef CONFIG_X86_64
3527	native_wrmsrl(MSR_GS_BASE, svm->host.gs_base);
3528#else
3529	loadsegment(fs, svm->host.fs);
3530#ifndef CONFIG_X86_32_LAZY_GS
3531	loadsegment(gs, svm->host.gs);
3532#endif
3533#endif
3534
3535	/*
3536	 * VMEXIT disables interrupts (host state), but tracing and lockdep
3537	 * have them in state 'on' as recorded before entering guest mode.
3538	 * Same as enter_from_user_mode().
3539	 *
3540	 * context_tracking_guest_exit() restores host context and reinstates
3541	 * RCU if enabled and required.
3542	 *
3543	 * This needs to be done before the below as native_read_msr()
3544	 * contains a tracepoint and x86_spec_ctrl_restore_host() calls
3545	 * into world and some more.
3546	 */
3547	lockdep_hardirqs_off(CALLER_ADDR0);
3548	context_tracking_guest_exit();
3549
3550	instrumentation_begin();
3551	trace_hardirqs_off_finish();
3552	instrumentation_end();
3553}
3554
3555static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
3556{
3557	struct vcpu_svm *svm = to_svm(vcpu);
3558
3559	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
3560	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
3561	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
3562
3563	/*
3564	 * Disable singlestep if we're injecting an interrupt/exception.
3565	 * We don't want our modified rflags to be pushed on the stack where
3566	 * we might not be able to easily reset them if we disabled NMI
3567	 * singlestep later.
3568	 */
3569	if (svm->nmi_singlestep && svm->vmcb->control.event_inj) {
3570		/*
3571		 * Event injection happens before external interrupts cause a
3572		 * vmexit and interrupts are disabled here, so smp_send_reschedule
3573		 * is enough to force an immediate vmexit.
3574		 */
3575		disable_nmi_singlestep(svm);
3576		smp_send_reschedule(vcpu->cpu);
3577	}
3578
3579	pre_svm_run(svm);
3580
3581	sync_lapic_to_cr8(vcpu);
3582
3583	svm->vmcb->save.cr2 = vcpu->arch.cr2;
3584
3585	/*
3586	 * Run with all-zero DR6 unless needed, so that we can get the exact cause
3587	 * of a #DB.
3588	 */
3589	if (unlikely(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
3590		svm_set_dr6(svm, vcpu->arch.dr6);
3591	else
3592		svm_set_dr6(svm, DR6_FIXED_1 | DR6_RTM);
3593
3594	clgi();
3595	kvm_load_guest_xsave_state(vcpu);
3596
3597	kvm_wait_lapic_expire(vcpu);
3598
3599	/*
3600	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
3601	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
3602	 * is no need to worry about the conditional branch over the wrmsr
3603	 * being speculatively taken.
3604	 */
3605	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
3606
3607	svm_vcpu_enter_exit(vcpu, svm);
3608
3609	/*
3610	 * We do not use IBRS in the kernel. If this vCPU has used the
3611	 * SPEC_CTRL MSR it may have left it on; save the value and
3612	 * turn it off. This is much more efficient than blindly adding
3613	 * it to the atomic save/restore list. Especially as the former
3614	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
3615	 *
3616	 * For non-nested case:
3617	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
3618	 * save it.
3619	 *
3620	 * For nested case:
3621	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
3622	 * save it.
3623	 */
3624	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
3625		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
3626
3627	reload_tss(vcpu);
3628
3629	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
3630
3631	vcpu->arch.cr2 = svm->vmcb->save.cr2;
3632	vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax;
3633	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
3634	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
3635
3636	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
3637		kvm_before_interrupt(&svm->vcpu);
3638
3639	kvm_load_host_xsave_state(vcpu);
3640	stgi();
3641
3642	/* Any pending NMI will happen here */
3643
3644	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
3645		kvm_after_interrupt(&svm->vcpu);
3646
3647	sync_cr8_to_lapic(vcpu);
3648
3649	svm->next_rip = 0;
3650	if (is_guest_mode(&svm->vcpu)) {
3651		sync_nested_vmcb_control(svm);
3652		svm->nested.nested_run_pending = 0;
3653	}
3654
3655	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
3656	vmcb_mark_all_clean(svm->vmcb);
3657
3658	/* if exit due to PF check for async PF */
3659	if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
3660		svm->vcpu.arch.apf.host_apf_flags =
3661			kvm_read_and_reset_apf_flags();
3662
3663	if (npt_enabled) {
3664		vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);
3665		vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR);
3666	}
3667
3668	/*
3669	 * We need to handle MC intercepts here before the vcpu has a chance to
3670	 * change the physical cpu
3671	 */
3672	if (unlikely(svm->vmcb->control.exit_code ==
3673		     SVM_EXIT_EXCP_BASE + MC_VECTOR))
3674		svm_handle_mce(svm);
3675
3676	svm_complete_interrupts(svm);
3677
3678	if (is_guest_mode(vcpu))
3679		return EXIT_FASTPATH_NONE;
3680
3681	return svm_exit_handlers_fastpath(vcpu);
3682}
3683
3684static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root,
3685			     int root_level)
3686{
3687	struct vcpu_svm *svm = to_svm(vcpu);
3688	unsigned long cr3;
3689
3690	cr3 = __sme_set(root);
3691	if (npt_enabled) {
3692		svm->vmcb->control.nested_cr3 = cr3;
3693		vmcb_mark_dirty(svm->vmcb, VMCB_NPT);
3694
3695		/* Loading L2's CR3 is handled by enter_svm_guest_mode.  */
3696		if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
3697			return;
3698		cr3 = vcpu->arch.cr3;
3699	}
3700
3701	svm->vmcb->save.cr3 = cr3;
3702	vmcb_mark_dirty(svm->vmcb, VMCB_CR);
3703}
3704
3705static int is_disabled(void)
3706{
3707	u64 vm_cr;
3708
3709	rdmsrl(MSR_VM_CR, vm_cr);
3710	if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE))
3711		return 1;
3712
3713	return 0;
3714}
3715
3716static void
3717svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
3718{
3719	/*
3720	 * Patch in the VMMCALL instruction:
3721	 */
3722	hypercall[0] = 0x0f;
3723	hypercall[1] = 0x01;
3724	hypercall[2] = 0xd9;
3725}
3726
3727static int __init svm_check_processor_compat(void)
3728{
3729	return 0;
3730}
3731
3732static bool svm_cpu_has_accelerated_tpr(void)
3733{
3734	return false;
3735}
3736
3737static bool svm_has_emulated_msr(u32 index)
3738{
3739	switch (index) {
3740	case MSR_IA32_MCG_EXT_CTL:
3741	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
3742		return false;
3743	default:
3744		break;
3745	}
3746
3747	return true;
3748}
3749
3750static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
3751{
3752	return 0;
3753}
3754
3755static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
3756{
3757	struct vcpu_svm *svm = to_svm(vcpu);
3758	struct kvm_cpuid_entry2 *best;
3759
3760	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
3761				    boot_cpu_has(X86_FEATURE_XSAVE) &&
3762				    boot_cpu_has(X86_FEATURE_XSAVES);
3763
3764	/* Update nrips enabled cache */
3765	svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) &&
3766			     guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS);
3767
3768	/* Check again if INVPCID interception if required */
3769	svm_check_invpcid(svm);
3770
3771	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
3772	if (sev_guest(vcpu->kvm)) {
3773		best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0);
3774		if (best)
3775			vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f));
3776	}
3777
3778	if (!kvm_vcpu_apicv_active(vcpu))
3779		return;
3780
3781	/*
3782	 * AVIC does not work with an x2APIC mode guest. If the X2APIC feature
3783	 * is exposed to the guest, disable AVIC.
3784	 */
3785	if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC))
3786		kvm_request_apicv_update(vcpu->kvm, false,
3787					 APICV_INHIBIT_REASON_X2APIC);
3788
3789	/*
3790	 * Currently, AVIC does not work with nested virtualization.
3791	 * So, we disable AVIC when cpuid for SVM is set in the L1 guest.
3792	 */
3793	if (nested && guest_cpuid_has(vcpu, X86_FEATURE_SVM))
3794		kvm_request_apicv_update(vcpu->kvm, false,
3795					 APICV_INHIBIT_REASON_NESTED);
3796}
3797
3798static bool svm_has_wbinvd_exit(void)
3799{
3800	return true;
3801}
3802
3803#define PRE_EX(exit)  { .exit_code = (exit), \
3804			.stage = X86_ICPT_PRE_EXCEPT, }
3805#define POST_EX(exit) { .exit_code = (exit), \
3806			.stage = X86_ICPT_POST_EXCEPT, }
3807#define POST_MEM(exit) { .exit_code = (exit), \
3808			.stage = X86_ICPT_POST_MEMACCESS, }
3809
3810static const struct __x86_intercept {
3811	u32 exit_code;
3812	enum x86_intercept_stage stage;
3813} x86_intercept_map[] = {
3814	[x86_intercept_cr_read]		= POST_EX(SVM_EXIT_READ_CR0),
3815	[x86_intercept_cr_write]	= POST_EX(SVM_EXIT_WRITE_CR0),
3816	[x86_intercept_clts]		= POST_EX(SVM_EXIT_WRITE_CR0),
3817	[x86_intercept_lmsw]		= POST_EX(SVM_EXIT_WRITE_CR0),
3818	[x86_intercept_smsw]		= POST_EX(SVM_EXIT_READ_CR0),
3819	[x86_intercept_dr_read]		= POST_EX(SVM_EXIT_READ_DR0),
3820	[x86_intercept_dr_write]	= POST_EX(SVM_EXIT_WRITE_DR0),
3821	[x86_intercept_sldt]		= POST_EX(SVM_EXIT_LDTR_READ),
3822	[x86_intercept_str]		= POST_EX(SVM_EXIT_TR_READ),
3823	[x86_intercept_lldt]		= POST_EX(SVM_EXIT_LDTR_WRITE),
3824	[x86_intercept_ltr]		= POST_EX(SVM_EXIT_TR_WRITE),
3825	[x86_intercept_sgdt]		= POST_EX(SVM_EXIT_GDTR_READ),
3826	[x86_intercept_sidt]		= POST_EX(SVM_EXIT_IDTR_READ),
3827	[x86_intercept_lgdt]		= POST_EX(SVM_EXIT_GDTR_WRITE),
3828	[x86_intercept_lidt]		= POST_EX(SVM_EXIT_IDTR_WRITE),
3829	[x86_intercept_vmrun]		= POST_EX(SVM_EXIT_VMRUN),
3830	[x86_intercept_vmmcall]		= POST_EX(SVM_EXIT_VMMCALL),
3831	[x86_intercept_vmload]		= POST_EX(SVM_EXIT_VMLOAD),
3832	[x86_intercept_vmsave]		= POST_EX(SVM_EXIT_VMSAVE),
3833	[x86_intercept_stgi]		= POST_EX(SVM_EXIT_STGI),
3834	[x86_intercept_clgi]		= POST_EX(SVM_EXIT_CLGI),
3835	[x86_intercept_skinit]		= POST_EX(SVM_EXIT_SKINIT),
3836	[x86_intercept_invlpga]		= POST_EX(SVM_EXIT_INVLPGA),
3837	[x86_intercept_rdtscp]		= POST_EX(SVM_EXIT_RDTSCP),
3838	[x86_intercept_monitor]		= POST_MEM(SVM_EXIT_MONITOR),
3839	[x86_intercept_mwait]		= POST_EX(SVM_EXIT_MWAIT),
3840	[x86_intercept_invlpg]		= POST_EX(SVM_EXIT_INVLPG),
3841	[x86_intercept_invd]		= POST_EX(SVM_EXIT_INVD),
3842	[x86_intercept_wbinvd]		= POST_EX(SVM_EXIT_WBINVD),
3843	[x86_intercept_wrmsr]		= POST_EX(SVM_EXIT_MSR),
3844	[x86_intercept_rdtsc]		= POST_EX(SVM_EXIT_RDTSC),
3845	[x86_intercept_rdmsr]		= POST_EX(SVM_EXIT_MSR),
3846	[x86_intercept_rdpmc]		= POST_EX(SVM_EXIT_RDPMC),
3847	[x86_intercept_cpuid]		= PRE_EX(SVM_EXIT_CPUID),
3848	[x86_intercept_rsm]		= PRE_EX(SVM_EXIT_RSM),
3849	[x86_intercept_pause]		= PRE_EX(SVM_EXIT_PAUSE),
3850	[x86_intercept_pushf]		= PRE_EX(SVM_EXIT_PUSHF),
3851	[x86_intercept_popf]		= PRE_EX(SVM_EXIT_POPF),
3852	[x86_intercept_intn]		= PRE_EX(SVM_EXIT_SWINT),
3853	[x86_intercept_iret]		= PRE_EX(SVM_EXIT_IRET),
3854	[x86_intercept_icebp]		= PRE_EX(SVM_EXIT_ICEBP),
3855	[x86_intercept_hlt]		= POST_EX(SVM_EXIT_HLT),
3856	[x86_intercept_in]		= POST_EX(SVM_EXIT_IOIO),
3857	[x86_intercept_ins]		= POST_EX(SVM_EXIT_IOIO),
3858	[x86_intercept_out]		= POST_EX(SVM_EXIT_IOIO),
3859	[x86_intercept_outs]		= POST_EX(SVM_EXIT_IOIO),
3860	[x86_intercept_xsetbv]		= PRE_EX(SVM_EXIT_XSETBV),
3861};
3862
3863#undef PRE_EX
3864#undef POST_EX
3865#undef POST_MEM
3866
3867static int svm_check_intercept(struct kvm_vcpu *vcpu,
3868			       struct x86_instruction_info *info,
3869			       enum x86_intercept_stage stage,
3870			       struct x86_exception *exception)
3871{
3872	struct vcpu_svm *svm = to_svm(vcpu);
3873	int vmexit, ret = X86EMUL_CONTINUE;
3874	struct __x86_intercept icpt_info;
3875	struct vmcb *vmcb = svm->vmcb;
3876
3877	if (info->intercept >= ARRAY_SIZE(x86_intercept_map))
3878		goto out;
3879
3880	icpt_info = x86_intercept_map[info->intercept];
3881
3882	if (stage != icpt_info.stage)
3883		goto out;
3884
3885	switch (icpt_info.exit_code) {
3886	case SVM_EXIT_READ_CR0:
3887		if (info->intercept == x86_intercept_cr_read)
3888			icpt_info.exit_code += info->modrm_reg;
3889		break;
3890	case SVM_EXIT_WRITE_CR0: {
3891		unsigned long cr0, val;
3892
3893		if (info->intercept == x86_intercept_cr_write)
3894			icpt_info.exit_code += info->modrm_reg;
3895
3896		if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0 ||
3897		    info->intercept == x86_intercept_clts)
3898			break;
3899
3900		if (!(vmcb_is_intercept(&svm->nested.ctl,
3901					INTERCEPT_SELECTIVE_CR0)))
3902			break;
3903
3904		cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK;
3905		val = info->src_val  & ~SVM_CR0_SELECTIVE_MASK;
3906
3907		if (info->intercept == x86_intercept_lmsw) {
3908			cr0 &= 0xfUL;
3909			val &= 0xfUL;
3910			/* lmsw can't clear PE - catch this here */
3911			if (cr0 & X86_CR0_PE)
3912				val |= X86_CR0_PE;
3913		}
3914
3915		if (cr0 ^ val)
3916			icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE;
3917
3918		break;
3919	}
3920	case SVM_EXIT_READ_DR0:
3921	case SVM_EXIT_WRITE_DR0:
3922		icpt_info.exit_code += info->modrm_reg;
3923		break;
3924	case SVM_EXIT_MSR:
3925		if (info->intercept == x86_intercept_wrmsr)
3926			vmcb->control.exit_info_1 = 1;
3927		else
3928			vmcb->control.exit_info_1 = 0;
3929		break;
3930	case SVM_EXIT_PAUSE:
3931		/*
3932		 * We get this for NOP only, but pause
3933		 * is rep not, check this here
3934		 */
3935		if (info->rep_prefix != REPE_PREFIX)
3936			goto out;
3937		break;
3938	case SVM_EXIT_IOIO: {
3939		u64 exit_info;
3940		u32 bytes;
3941
3942		if (info->intercept == x86_intercept_in ||
3943		    info->intercept == x86_intercept_ins) {
3944			exit_info = ((info->src_val & 0xffff) << 16) |
3945				SVM_IOIO_TYPE_MASK;
3946			bytes = info->dst_bytes;
3947		} else {
3948			exit_info = (info->dst_val & 0xffff) << 16;
3949			bytes = info->src_bytes;
3950		}
3951
3952		if (info->intercept == x86_intercept_outs ||
3953		    info->intercept == x86_intercept_ins)
3954			exit_info |= SVM_IOIO_STR_MASK;
3955
3956		if (info->rep_prefix)
3957			exit_info |= SVM_IOIO_REP_MASK;
3958
3959		bytes = min(bytes, 4u);
3960
3961		exit_info |= bytes << SVM_IOIO_SIZE_SHIFT;
3962
3963		exit_info |= (u32)info->ad_bytes << (SVM_IOIO_ASIZE_SHIFT - 1);
3964
3965		vmcb->control.exit_info_1 = exit_info;
3966		vmcb->control.exit_info_2 = info->next_rip;
3967
3968		break;
3969	}
3970	default:
3971		break;
3972	}
3973
3974	/* TODO: Advertise NRIPS to guest hypervisor unconditionally */
3975	if (static_cpu_has(X86_FEATURE_NRIPS))
3976		vmcb->control.next_rip  = info->next_rip;
3977	vmcb->control.exit_code = icpt_info.exit_code;
3978	vmexit = nested_svm_exit_handled(svm);
3979
3980	ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED
3981					   : X86EMUL_CONTINUE;
3982
3983out:
3984	return ret;
3985}
3986
3987static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
3988{
3989	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR)
3990		vcpu->arch.at_instruction_boundary = true;
3991}
3992
3993static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
3994{
3995	if (!kvm_pause_in_guest(vcpu->kvm))
3996		shrink_ple_window(vcpu);
3997}
3998
3999static void svm_setup_mce(struct kvm_vcpu *vcpu)
4000{
4001	/* [63:9] are reserved. */
4002	vcpu->arch.mcg_cap &= 0x1ff;
4003}
4004
4005bool svm_smi_blocked(struct kvm_vcpu *vcpu)
4006{
4007	struct vcpu_svm *svm = to_svm(vcpu);
4008
4009	/* Per APM Vol.2 15.22.2 "Response to SMI" */
4010	if (!gif_set(svm))
4011		return true;
4012
4013	return is_smm(vcpu);
4014}
4015
4016static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
4017{
4018	struct vcpu_svm *svm = to_svm(vcpu);
4019	if (svm->nested.nested_run_pending)
4020		return -EBUSY;
4021
4022	/* An SMI must not be injected into L2 if it's supposed to VM-Exit.  */
4023	if (for_injection && is_guest_mode(vcpu) && nested_exit_on_smi(svm))
4024		return -EBUSY;
4025
4026	return !svm_smi_blocked(vcpu);
4027}
4028
4029static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
4030{
4031	struct vcpu_svm *svm = to_svm(vcpu);
4032	int ret;
4033
4034	if (is_guest_mode(vcpu)) {
4035		/* FED8h - SVM Guest */
4036		put_smstate(u64, smstate, 0x7ed8, 1);
4037		/* FEE0h - SVM Guest VMCB Physical Address */
4038		put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
4039
4040		svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
4041		svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
4042		svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
4043
4044		ret = nested_svm_vmexit(svm);
4045		if (ret)
4046			return ret;
4047	}
4048	return 0;
4049}
4050
4051static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
4052{
4053	struct vcpu_svm *svm = to_svm(vcpu);
4054	struct kvm_host_map map;
4055	int ret = 0;
4056
4057	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
4058		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
4059		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
4060		u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
4061
4062		if (guest) {
4063			if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
4064				return 1;
4065
4066			if (!(saved_efer & EFER_SVME))
4067				return 1;
4068
4069			if (kvm_vcpu_map(&svm->vcpu,
4070					 gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
4071				return 1;
4072
4073			if (svm_allocate_nested(svm))
4074				return 1;
4075
4076			ret = enter_svm_guest_mode(svm, vmcb12_gpa, map.hva);
4077			kvm_vcpu_unmap(&svm->vcpu, &map, true);
4078		}
4079	}
4080
4081	return ret;
4082}
4083
4084static void enable_smi_window(struct kvm_vcpu *vcpu)
4085{
4086	struct vcpu_svm *svm = to_svm(vcpu);
4087
4088	if (!gif_set(svm)) {
4089		if (vgif_enabled(svm))
4090			svm_set_intercept(svm, INTERCEPT_STGI);
4091		/* STGI will cause a vm exit */
4092	} else {
4093		/* We must be in SMM; RSM will cause a vmexit anyway.  */
4094	}
4095}
4096
4097static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len)
4098{
4099	bool smep, smap, is_user;
4100	unsigned long cr4;
4101
4102	/* Emulation is always possible when KVM has access to all guest state. */
4103	if (!sev_guest(vcpu->kvm))
4104		return true;
4105
4106	/*
4107	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
4108	 *
4109	 * Errata:
4110	 * When CPU raise #NPF on guest data access and vCPU CR4.SMAP=1, it is
4111	 * possible that CPU microcode implementing DecodeAssist will fail
4112	 * to read bytes of instruction which caused #NPF. In this case,
4113	 * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly
4114	 * return 0 instead of the correct guest instruction bytes.
4115	 *
4116	 * This happens because CPU microcode reading instruction bytes
4117	 * uses a special opcode which attempts to read data using CPL=0
4118	 * priviledges. The microcode reads CS:RIP and if it hits a SMAP
4119	 * fault, it gives up and returns no instruction bytes.
4120	 *
4121	 * Detection:
4122	 * We reach here in case CPU supports DecodeAssist, raised #NPF and
4123	 * returned 0 in GuestIntrBytes field of the VMCB.
4124	 * First, errata can only be triggered in case vCPU CR4.SMAP=1.
4125	 * Second, if vCPU CR4.SMEP=1, errata could only be triggered
4126	 * in case vCPU CPL==3 (Because otherwise guest would have triggered
4127	 * a SMEP fault instead of #NPF).
4128	 * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL.
4129	 * As most guests enable SMAP if they have also enabled SMEP, use above
4130	 * logic in order to attempt minimize false-positive of detecting errata
4131	 * while still preserving all cases semantic correctness.
4132	 *
4133	 * Workaround:
4134	 * To determine what instruction the guest was executing, the hypervisor
4135	 * will have to decode the instruction at the instruction pointer.
4136	 *
4137	 * In non SEV guest, hypervisor will be able to read the guest
4138	 * memory to decode the instruction pointer when insn_len is zero
4139	 * so we return true to indicate that decoding is possible.
4140	 *
4141	 * But in the SEV guest, the guest memory is encrypted with the
4142	 * guest specific key and hypervisor will not be able to decode the
4143	 * instruction pointer so we will not able to workaround it. Lets
4144	 * print the error and request to kill the guest.
4145	 */
4146	if (likely(!insn || insn_len))
4147		return true;
4148
4149	cr4 = kvm_read_cr4(vcpu);
4150	smep = cr4 & X86_CR4_SMEP;
4151	smap = cr4 & X86_CR4_SMAP;
4152	is_user = svm_get_cpl(vcpu) == 3;
4153	if (smap && (!smep || is_user)) {
4154		pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n");
4155
4156		/*
4157		 * If the fault occurred in userspace, arbitrarily inject #GP
4158		 * to avoid killing the guest and to hopefully avoid confusing
4159		 * the guest kernel too much, e.g. injecting #PF would not be
4160		 * coherent with respect to the guest's page tables.  Request
4161		 * triple fault if the fault occurred in the kernel as there's
4162		 * no fault that KVM can inject without confusing the guest.
4163		 * In practice, the triple fault is moot as no sane SEV kernel
4164		 * will execute from user memory while also running with SMAP=1.
4165		 */
4166		if (is_user)
4167			kvm_inject_gp(vcpu, 0);
4168		else
4169			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
4170	}
4171
4172	return false;
4173}
4174
4175static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
4176{
4177	struct vcpu_svm *svm = to_svm(vcpu);
4178
4179	/*
4180	 * TODO: Last condition latch INIT signals on vCPU when
4181	 * vCPU is in guest-mode and vmcb12 defines intercept on INIT.
4182	 * To properly emulate the INIT intercept,
4183	 * svm_check_nested_events() should call nested_svm_vmexit()
4184	 * if an INIT signal is pending.
4185	 */
4186	return !gif_set(svm) ||
4187		   (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT));
4188}
4189
4190static void svm_vm_destroy(struct kvm *kvm)
4191{
4192	avic_vm_destroy(kvm);
4193	sev_vm_destroy(kvm);
4194}
4195
4196static int svm_vm_init(struct kvm *kvm)
4197{
4198	if (!pause_filter_count || !pause_filter_thresh)
4199		kvm->arch.pause_in_guest = true;
4200
4201	if (avic) {
4202		int ret = avic_vm_init(kvm);
4203		if (ret)
4204			return ret;
4205	}
4206
4207	kvm_apicv_init(kvm, avic);
4208	return 0;
4209}
4210
4211static struct kvm_x86_ops svm_x86_ops __initdata = {
4212	.hardware_unsetup = svm_hardware_teardown,
4213	.hardware_enable = svm_hardware_enable,
4214	.hardware_disable = svm_hardware_disable,
4215	.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
4216	.has_emulated_msr = svm_has_emulated_msr,
4217
4218	.vcpu_create = svm_create_vcpu,
4219	.vcpu_free = svm_free_vcpu,
4220	.vcpu_reset = svm_vcpu_reset,
4221
4222	.vm_size = sizeof(struct kvm_svm),
4223	.vm_init = svm_vm_init,
4224	.vm_destroy = svm_vm_destroy,
4225
4226	.prepare_guest_switch = svm_prepare_guest_switch,
4227	.vcpu_load = svm_vcpu_load,
4228	.vcpu_put = svm_vcpu_put,
4229	.vcpu_blocking = svm_vcpu_blocking,
4230	.vcpu_unblocking = svm_vcpu_unblocking,
4231
4232	.update_exception_bitmap = update_exception_bitmap,
4233	.get_msr_feature = svm_get_msr_feature,
4234	.get_msr = svm_get_msr,
4235	.set_msr = svm_set_msr,
4236	.get_segment_base = svm_get_segment_base,
4237	.get_segment = svm_get_segment,
4238	.set_segment = svm_set_segment,
4239	.get_cpl = svm_get_cpl,
4240	.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
4241	.set_cr0 = svm_set_cr0,
4242	.is_valid_cr4 = svm_is_valid_cr4,
4243	.set_cr4 = svm_set_cr4,
4244	.set_efer = svm_set_efer,
4245	.get_idt = svm_get_idt,
4246	.set_idt = svm_set_idt,
4247	.get_gdt = svm_get_gdt,
4248	.set_gdt = svm_set_gdt,
4249	.set_dr7 = svm_set_dr7,
4250	.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
4251	.cache_reg = svm_cache_reg,
4252	.get_rflags = svm_get_rflags,
4253	.set_rflags = svm_set_rflags,
4254
4255	.tlb_flush_all = svm_flush_tlb,
4256	.tlb_flush_current = svm_flush_tlb,
4257	.tlb_flush_gva = svm_flush_tlb_gva,
4258	.tlb_flush_guest = svm_flush_tlb,
4259
4260	.run = svm_vcpu_run,
4261	.handle_exit = handle_exit,
4262	.skip_emulated_instruction = skip_emulated_instruction,
4263	.update_emulated_instruction = NULL,
4264	.set_interrupt_shadow = svm_set_interrupt_shadow,
4265	.get_interrupt_shadow = svm_get_interrupt_shadow,
4266	.patch_hypercall = svm_patch_hypercall,
4267	.set_irq = svm_set_irq,
4268	.set_nmi = svm_inject_nmi,
4269	.queue_exception = svm_queue_exception,
4270	.cancel_injection = svm_cancel_injection,
4271	.interrupt_allowed = svm_interrupt_allowed,
4272	.nmi_allowed = svm_nmi_allowed,
4273	.get_nmi_mask = svm_get_nmi_mask,
4274	.set_nmi_mask = svm_set_nmi_mask,
4275	.enable_nmi_window = enable_nmi_window,
4276	.enable_irq_window = enable_irq_window,
4277	.update_cr8_intercept = update_cr8_intercept,
4278	.set_virtual_apic_mode = svm_set_virtual_apic_mode,
4279	.refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl,
4280	.check_apicv_inhibit_reasons = svm_check_apicv_inhibit_reasons,
4281	.pre_update_apicv_exec_ctrl = svm_pre_update_apicv_exec_ctrl,
4282	.load_eoi_exitmap = svm_load_eoi_exitmap,
4283	.hwapic_irr_update = svm_hwapic_irr_update,
4284	.hwapic_isr_update = svm_hwapic_isr_update,
4285	.sync_pir_to_irr = kvm_lapic_find_highest_irr,
4286	.apicv_post_state_restore = avic_post_state_restore,
4287
4288	.set_tss_addr = svm_set_tss_addr,
4289	.set_identity_map_addr = svm_set_identity_map_addr,
4290	.get_mt_mask = svm_get_mt_mask,
4291
4292	.get_exit_info = svm_get_exit_info,
4293
4294	.vcpu_after_set_cpuid = svm_vcpu_after_set_cpuid,
4295
4296	.has_wbinvd_exit = svm_has_wbinvd_exit,
4297
4298	.write_l1_tsc_offset = svm_write_l1_tsc_offset,
4299
4300	.load_mmu_pgd = svm_load_mmu_pgd,
4301
4302	.check_intercept = svm_check_intercept,
4303	.handle_exit_irqoff = svm_handle_exit_irqoff,
4304
4305	.request_immediate_exit = __kvm_request_immediate_exit,
4306
4307	.sched_in = svm_sched_in,
4308
4309	.pmu_ops = &amd_pmu_ops,
4310	.nested_ops = &svm_nested_ops,
4311
4312	.deliver_posted_interrupt = svm_deliver_avic_intr,
4313	.dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt,
4314	.update_pi_irte = svm_update_pi_irte,
4315	.setup_mce = svm_setup_mce,
4316
4317	.smi_allowed = svm_smi_allowed,
4318	.pre_enter_smm = svm_pre_enter_smm,
4319	.pre_leave_smm = svm_pre_leave_smm,
4320	.enable_smi_window = enable_smi_window,
4321
4322	.mem_enc_op = svm_mem_enc_op,
4323	.mem_enc_reg_region = svm_register_enc_region,
4324	.mem_enc_unreg_region = svm_unregister_enc_region,
4325	.guest_memory_reclaimed = sev_guest_memory_reclaimed,
4326
4327	.can_emulate_instruction = svm_can_emulate_instruction,
4328
4329	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
4330
4331	.msr_filter_changed = svm_msr_filter_changed,
4332};
4333
4334static struct kvm_x86_init_ops svm_init_ops __initdata = {
4335	.cpu_has_kvm_support = has_svm,
4336	.disabled_by_bios = is_disabled,
4337	.hardware_setup = svm_hardware_setup,
4338	.check_processor_compatibility = svm_check_processor_compat,
4339
4340	.runtime_ops = &svm_x86_ops,
4341};
4342
4343static int __init svm_init(void)
4344{
4345	__unused_size_checks();
4346
4347	return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm),
4348			__alignof__(struct vcpu_svm), THIS_MODULE);
4349}
4350
4351static void __exit svm_exit(void)
4352{
4353	kvm_exit();
4354}
4355
4356module_init(svm_init)
4357module_exit(svm_exit)
4358