1 files changed, 211 insertions, 123 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 661e2bf38526..cf917139de6b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -68,6 +68,7 @@
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/intel_pt.h>
+#include <asm/emulate_prefix.h>
 #include <clocksource/hyperv_timer.h>
 
 #define CREATE_TRACE_POINTS
@@ -176,6 +177,8 @@ struct kvm_shared_msrs {
 static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
 static struct kvm_shared_msrs __percpu *shared_msrs;
 
+static u64 __read_mostly host_xss;
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pf_fixed", VCPU_STAT(pf_fixed) },
 	{ "pf_guest", VCPU_STAT(pf_guest) },
@@ -213,6 +216,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
 	{ "largepages", VM_STAT(lpages, .mode = 0444) },
+	{ "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) },
 	{ "max_mmu_page_hash_collisions",
 		VM_STAT(max_mmu_page_hash_collisions) },
 	{ NULL }
@@ -259,23 +263,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	}
 }
 
-static void shared_msr_update(unsigned slot, u32 msr)
-{
-	u64 value;
-	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
-
-	/* only read, and nobody should modify it at this time,
-	 * so don't need lock */
-	if (slot >= shared_msrs_global.nr) {
-		printk(KERN_ERR "kvm: invalid MSR slot!");
-		return;
-	}
-	rdmsrl_safe(msr, &value);
-	smsr->values[slot].host = value;
-	smsr->values[slot].curr = value;
-}
-
 void kvm_define_shared_msr(unsigned slot, u32 msr)
 {
 	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
@@ -287,10 +274,16 @@ EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
 
 static void kvm_shared_msr_cpu_online(void)
 {
-	unsigned i;
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	u64 value;
+	int i;
 
-	for (i = 0; i < shared_msrs_global.nr; ++i)
-		shared_msr_update(i, shared_msrs_global.msrs[i]);
+	for (i = 0; i < shared_msrs_global.nr; ++i) {
+		rdmsrl_safe(shared_msrs_global.msrs[i], &value);
+		smsr->values[i].host = value;
+		smsr->values[i].curr = value;
+	}
 }
 
 int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
@@ -299,13 +292,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 	int err;
 
-	if (((value ^ smsr->values[slot].curr) & mask) == 0)
+	value = (value & mask) | (smsr->values[slot].host & ~mask);
+	if (value == smsr->values[slot].curr)
 		return 0;
-	smsr->values[slot].curr = value;
 	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
+	smsr->values[slot].curr = value;
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
@@ -360,8 +354,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 asmlinkage __visible void kvm_spurious_fault(void)
 {
 	/* Fault while not rebooting.  We want the trace. */
-	if (!kvm_rebooting)
-		BUG();
+	BUG_ON(!kvm_rebooting);
 }
 EXPORT_SYMBOL_GPL(kvm_spurious_fault);
 
@@ -709,10 +702,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 	ret = 1;
 
 	memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs));
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_dirty);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
+
 out:
 
 	return ret;
@@ -722,7 +713,6 @@ EXPORT_SYMBOL_GPL(load_pdptrs);
 bool pdptrs_changed(struct kvm_vcpu *vcpu)
 {
 	u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
-	bool changed = true;
 	int offset;
 	gfn_t gfn;
 	int r;
@@ -730,8 +720,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	if (!is_pae_paging(vcpu))
 		return false;
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_avail))
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
 		return true;
 
 	gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
@@ -739,11 +728,9 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
 				       PFERR_USER_MASK | PFERR_WRITE_MASK);
 	if (r < 0)
-		goto out;
-	changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
-out:
+		return true;
 
-	return changed;
+	return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
 }
 EXPORT_SYMBOL_GPL(pdptrs_changed);
 
@@ -812,27 +799,34 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 {
-	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
-			!vcpu->guest_xcr0_loaded) {
-		/* kvm_set_xcr() also depends on this */
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
-		vcpu->guest_xcr0_loaded = 1;
+
+		if (vcpu->arch.xsaves_enabled &&
+		    vcpu->arch.ia32_xss != host_xss)
+			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
+EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
 
-void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_xcr0_loaded) {
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
-		vcpu->guest_xcr0_loaded = 0;
+
+		if (vcpu->arch.xsaves_enabled &&
+		    vcpu->arch.ia32_xss != host_xss)
+			wrmsrl(MSR_IA32_XSS, host_xss);
 	}
+
 }
-EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
+EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
 
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
@@ -984,7 +978,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush);
 	vcpu->arch.cr3 = cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	return 0;
 }
@@ -1133,13 +1127,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
  *
- * This list is modified at module load time to reflect the
+ * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
+ * extract the supported MSRs from the related const lists.
+ * msrs_to_save is selected from the msrs_to_save_all to reflect the
  * capabilities of the host cpu. This capabilities test skips MSRs that are
- * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
+ * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
  * may depend on host virtualization features rather than host cpu features.
  */
 
-static u32 msrs_to_save[] = {
+static const u32 msrs_to_save_all[] = {
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64
@@ -1180,9 +1176,10 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
 };
 
+static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
 static unsigned num_msrs_to_save;
 
-static u32 emulated_msrs[] = {
+static const u32 emulated_msrs_all[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
@@ -1221,7 +1218,7 @@ static u32 emulated_msrs[] = {
 	 * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
 	 * We always support the "true" VMX control MSRs, even if the host
 	 * processor does not, so I am putting these registers here rather
-	 * than in msrs_to_save.
+	 * than in msrs_to_save_all.
 	 */
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
@@ -1240,13 +1237,14 @@ static u32 emulated_msrs[] = {
 	MSR_KVM_POLL_CONTROL,
 };
 
+static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
 static unsigned num_emulated_msrs;
 
 /*
  * List of msr numbers which are used to expose MSR-based features that
  * can be used by a hypervisor to validate requested CPU features.
  */
-static u32 msr_based_features[] = {
+static const u32 msr_based_features_all[] = {
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
 	MSR_IA32_VMX_PINBASED_CTLS,
@@ -1271,6 +1269,7 @@ static u32 msr_based_features[] = {
 	MSR_IA32_ARCH_CAPABILITIES,
 };
 
+static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
 static unsigned int num_msr_based_features;
 
 static u64 kvm_get_arch_capabilities(void)
@@ -1281,6 +1280,14 @@ static u64 kvm_get_arch_capabilities(void)
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
 
 	/*
+	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
+	 * the nested hypervisor runs with NX huge pages.  If it is not,
+	 * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
+	 * L1 guests, so it need not worry about its own (L2) guests.
+	 */
+	data |= ARCH_CAP_PSCHANGE_MC_NO;
+
+	/*
 	 * If we're doing cache flushes (either "always" or "cond")
 	 * we will do one whenever the guest does a vmlaunch/vmresume.
 	 * If an outer hypervisor is doing the cache flush for us
@@ -1299,6 +1306,17 @@ static u64 kvm_get_arch_capabilities(void)
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
 		data |= ARCH_CAP_MDS_NO;
 
+	/*
+	 * On TAA affected systems:
+	 *      - nothing to do if TSX is disabled on the host.
+	 *      - we emulate TSX_CTRL if present on the host.
+	 *	  This lets the guest use VERW to clear CPU buffers.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_RTM))
+		data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR);
+	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+		data |= ARCH_CAP_TAA_NO;
+
 	return data;
 }
 
@@ -1445,8 +1463,8 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
-static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
-			 bool host_initiated)
+int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
+		  bool host_initiated)
 {
 	struct msr_data msr;
 	int ret;
@@ -1521,20 +1539,25 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 }
 
 #ifdef CONFIG_X86_64
+struct pvclock_clock {
+	int vclock_mode;
+	u64 cycle_last;
+	u64 mask;
+	u32 mult;
+	u32 shift;
+};
+
 struct pvclock_gtod_data {
 	seqcount_t	seq;
 
-	struct { /* extract of a clocksource struct */
-		int vclock_mode;
-		u64	cycle_last;
-		u64	mask;
-		u32	mult;
-		u32	shift;
-	} clock;
+	struct pvclock_clock clock; /* extract of a clocksource struct */
+	struct pvclock_clock raw_clock; /* extract of a clocksource struct */
 
+	u64		boot_ns_raw;
 	u64		boot_ns;
 	u64		nsec_base;
 	u64		wall_time_sec;
+	u64		monotonic_raw_nsec;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1542,9 +1565,10 @@ static struct pvclock_gtod_data pvclock_gtod_data;
 static void update_pvclock_gtod(struct timekeeper *tk)
 {
 	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
-	u64 boot_ns;
+	u64 boot_ns, boot_ns_raw;
 
 	boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot));
+	boot_ns_raw = ktime_to_ns(ktime_add(tk->tkr_raw.base, tk->offs_boot));
 
 	write_seqcount_begin(&vdata->seq);
 
@@ -1555,11 +1579,20 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 	vdata->clock.mult		= tk->tkr_mono.mult;
 	vdata->clock.shift		= tk->tkr_mono.shift;
 
+	vdata->raw_clock.vclock_mode	= tk->tkr_raw.clock->archdata.vclock_mode;
+	vdata->raw_clock.cycle_last	= tk->tkr_raw.cycle_last;
+	vdata->raw_clock.mask		= tk->tkr_raw.mask;
+	vdata->raw_clock.mult		= tk->tkr_raw.mult;
+	vdata->raw_clock.shift		= tk->tkr_raw.shift;
+
 	vdata->boot_ns			= boot_ns;
 	vdata->nsec_base		= tk->tkr_mono.xtime_nsec;
 
 	vdata->wall_time_sec            = tk->xtime_sec;
 
+	vdata->boot_ns_raw		= boot_ns_raw;
+	vdata->monotonic_raw_nsec	= tk->tkr_raw.xtime_nsec;
+
 	write_seqcount_end(&vdata->seq);
 }
 #endif
@@ -1983,21 +2016,21 @@ static u64 read_tsc(void)
 	return last;
 }
 
-static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
+static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp,
+			  int *mode)
 {
 	long v;
-	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	u64 tsc_pg_val;
 
-	switch (gtod->clock.vclock_mode) {
+	switch (clock->vclock_mode) {
 	case VCLOCK_HVCLOCK:
 		tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
 						  tsc_timestamp);
 		if (tsc_pg_val != U64_MAX) {
 			/* TSC page valid */
 			*mode = VCLOCK_HVCLOCK;
-			v = (tsc_pg_val - gtod->clock.cycle_last) &
-				gtod->clock.mask;
+			v = (tsc_pg_val - clock->cycle_last) &
+				clock->mask;
 		} else {
 			/* TSC page invalid */
 			*mode = VCLOCK_NONE;
@@ -2006,8 +2039,8 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 	case VCLOCK_TSC:
 		*mode = VCLOCK_TSC;
 		*tsc_timestamp = read_tsc();
-		v = (*tsc_timestamp - gtod->clock.cycle_last) &
-			gtod->clock.mask;
+		v = (*tsc_timestamp - clock->cycle_last) &
+			clock->mask;
 		break;
 	default:
 		*mode = VCLOCK_NONE;
@@ -2016,10 +2049,10 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 	if (*mode == VCLOCK_NONE)
 		*tsc_timestamp = v = 0;
 
-	return v * gtod->clock.mult;
+	return v * clock->mult;
 }
 
-static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
+static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
@@ -2028,10 +2061,10 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
 
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
-		ns = gtod->nsec_base;
-		ns += vgettsc(tsc_timestamp, &mode);
+		ns = gtod->monotonic_raw_nsec;
+		ns += vgettsc(&gtod->raw_clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
-		ns += gtod->boot_ns;
+		ns += gtod->boot_ns_raw;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	*t = ns;
 
@@ -2049,7 +2082,7 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
 		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->nsec_base;
-		ns += vgettsc(tsc_timestamp, &mode);
+		ns += vgettsc(&gtod->clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
@@ -2066,7 +2099,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
 	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
 		return false;
 
-	return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns,
+	return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns,
 						      tsc_timestamp));
 }
 
@@ -2537,6 +2570,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pv_time_enabled = false;
+	vcpu->arch.time = 0;
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
@@ -2688,6 +2722,20 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
+	case MSR_IA32_XSS:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+			return 1;
+		/*
+		 * We do support PT if kvm_x86_ops->pt_supported(), but we do
+		 * not support IA32_XSS[bit 8]. Guests will have to use
+		 * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT
+		 * MSRs.
+		 */
+		if (data != 0)
+			return 1;
+		vcpu->arch.ia32_xss = data;
+		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
 			return 1;
@@ -2702,8 +2750,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_KVM_SYSTEM_TIME: {
 		struct kvm_arch *ka = &vcpu->kvm->arch;
 
-		kvmclock_reset(vcpu);
-
 		if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) {
 			bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
 
@@ -2717,14 +2763,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
 		/* we verify if the enable bit is set... */
+		vcpu->arch.pv_time_enabled = false;
 		if (!(data & 1))
 			break;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
-			vcpu->arch.pv_time_enabled = false;
-		else
 			vcpu->arch.pv_time_enabled = true;
 
 		break;
@@ -3018,6 +3063,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return get_msr_mce(vcpu, msr_info->index, &msr_info->data,
 				   msr_info->host_initiated);
+	case MSR_IA32_XSS:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+			return 1;
+		msr_info->data = vcpu->arch.ia32_xss;
+		break;
 	case MSR_K7_CLK_CTL:
 		/*
 		 * Provide expected ramp-up count for K7. All other
@@ -3795,12 +3846,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
 				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-			if (lapic_in_kernel(vcpu)) {
-				if (events->smi.latched_init)
-					set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
-				else
-					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
-			}
+		}
+
+		if (lapic_in_kernel(vcpu)) {
+			if (events->smi.latched_init)
+				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			else
+				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 		}
 	}
 
@@ -4391,6 +4443,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_SET_NESTED_STATE: {
 		struct kvm_nested_state __user *user_kvm_nested_state = argp;
 		struct kvm_nested_state kvm_state;
+		int idx;
 
 		r = -EINVAL;
 		if (!kvm_x86_ops->set_nested_state)
@@ -4414,7 +4467,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
 			break;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_GET_SUPPORTED_HV_CPUID: {
@@ -4916,9 +4971,6 @@ set_identity_unlock:
 		if (!irqchip_kernel(kvm))
 			goto set_irqchip_out;
 		r = kvm_vm_ioctl_set_irqchip(kvm, chip);
-		if (r)
-			goto set_irqchip_out;
-		r = 0;
 	set_irqchip_out:
 		kfree(chip);
 		break;
@@ -5093,22 +5145,26 @@ static void kvm_init_msr_list(void)
 {
 	struct x86_pmu_capability x86_pmu;
 	u32 dummy[2];
-	unsigned i, j;
+	unsigned i;
 
 	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
-			 "Please update the fixed PMCs in msrs_to_save[]");
+			 "Please update the fixed PMCs in msrs_to_saved_all[]");
 
 	perf_get_x86_pmu_capability(&x86_pmu);
 
-	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
-		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
+	num_msrs_to_save = 0;
+	num_emulated_msrs = 0;
+	num_msr_based_features = 0;
+
+	for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) {
+		if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0)
 			continue;
 
 		/*
 		 * Even MSRs that are valid in the host may not be exposed
 		 * to the guests in some cases.
 		 */
-		switch (msrs_to_save[i]) {
+		switch (msrs_to_save_all[i]) {
 		case MSR_IA32_BNDCFGS:
 			if (!kvm_mpx_supported())
 				continue;
@@ -5136,17 +5192,17 @@ static void kvm_init_msr_list(void)
 			break;
 		case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: {
 			if (!kvm_x86_ops->pt_supported() ||
-				msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >=
+				msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >=
 				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
 				continue;
 			break;
 		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
-			if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
 			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
 				continue;
 			break;
 		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
-			if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
 			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
 				continue;
 		}
@@ -5154,34 +5210,25 @@ static void kvm_init_msr_list(void)
 			break;
 		}
 
-		if (j < i)
-			msrs_to_save[j] = msrs_to_save[i];
-		j++;
+		msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i];
 	}
-	num_msrs_to_save = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+	for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i]))
 			continue;
 
-		if (j < i)
-			emulated_msrs[j] = emulated_msrs[i];
-		j++;
+		emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
 	}
-	num_emulated_msrs = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+	for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
 		struct kvm_msr_entry msr;
 
-		msr.index = msr_based_features[i];
+		msr.index = msr_based_features_all[i];
 		if (kvm_get_msr_feature(&msr))
 			continue;
 
-		if (j < i)
-			msr_based_features[j] = msr_based_features[i];
-		j++;
+		msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
 	}
-	num_msr_based_features = j;
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -5446,6 +5493,7 @@ EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
 
 int handle_ud(struct kvm_vcpu *vcpu)
 {
+	static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX };
 	int emul_type = EMULTYPE_TRAP_UD;
 	char sig[5]; /* ud2; .ascii "kvm" */
 	struct x86_exception e;
@@ -5453,7 +5501,7 @@ int handle_ud(struct kvm_vcpu *vcpu)
 	if (force_emulation_prefix &&
 	    kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu),
 				sig, sizeof(sig), &e) == 0 &&
-	    memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) {
+	    memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) {
 		kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig));
 		emul_type = EMULTYPE_TRAP_UD_FORCED;
 	}
@@ -6111,7 +6159,7 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
 static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
 			      u32 pmc)
 {
-	return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc);
+	return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc);
 }
 
 static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
@@ -7841,6 +7889,19 @@ static void process_smi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
+void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
+				       unsigned long *vcpu_bitmap)
+{
+	cpumask_var_t cpus;
+
+	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+
+	kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC,
+				    vcpu_bitmap, cpus);
+
+	free_cpumask_var(cpus);
+}
+
 void kvm_make_scan_ioapic_request(struct kvm *kvm)
 {
 	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
@@ -7918,7 +7979,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 	 */
 	put_page(page);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
 
 void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
 {
@@ -7941,8 +8001,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_immediate_exit = false;
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu))
-			kvm_x86_ops->get_vmcs12_pages(vcpu);
+		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) {
+			if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) {
+				r = 0;
+				goto out;
+			}
+		}
 		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
@@ -8673,8 +8737,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	    mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
 		goto out;
 
-	/* INITs are latched while in SMM */
-	if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
+	/*
+	 * KVM_MP_STATE_INIT_RECEIVED means the processor is in
+	 * INIT state; latched init should be reported using
+	 * KVM_SET_VCPU_EVENTS, so reject it here.
+	 */
+	if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) &&
 	    (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
 	     mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
 		goto out;
@@ -8766,7 +8834,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr2 = sregs->cr2;
 	mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
 	vcpu->arch.cr3 = sregs->cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	kvm_set_cr8(vcpu, sregs->cr8);
 
@@ -9293,6 +9361,9 @@ int kvm_arch_hardware_setup(void)
 		kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		rdmsrl(MSR_IA32_XSS, host_xss);
+
 	kvm_init_msr_list();
 	return 0;
 }
@@ -9346,7 +9417,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_pio_data;
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
-		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
+		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm);
 		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
@@ -9415,7 +9486,13 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
 	vcpu->arch.l1tf_flush_l1d = true;
+	if (pmu->version && unlikely(pmu->event_count)) {
+		pmu->need_cleanup = true;
+		kvm_make_request(KVM_REQ_PMU, vcpu);
+	}
 	kvm_x86_ops->sched_in(vcpu, cpu);
 }
 
@@ -9427,6 +9504,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+	INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
@@ -9455,6 +9533,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	return kvm_x86_ops->vm_init(kvm);
 }
 
+int kvm_arch_post_init_vm(struct kvm *kvm)
+{
+	return kvm_mmu_post_init_vm(kvm);
+}
+
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 {
 	vcpu_load(vcpu);
@@ -9556,6 +9639,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 }
 EXPORT_SYMBOL_GPL(x86_set_memory_region);
 
+void kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+	kvm_mmu_pre_destroy_vm(kvm);
+}
+
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	if (current->mm == kvm->mm) {