1 files changed, 566 insertions, 128 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ce856e0ece84..397f599b20e5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -71,6 +71,7 @@
 #include <asm/irq_remapping.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
+#include <asm/tlbflush.h>
 #include <asm/intel_pt.h>
 #include <asm/emulate_prefix.h>
 #include <clocksource/hyperv_timer.h>
@@ -161,24 +162,29 @@ module_param(force_emulation_prefix, bool, S_IRUGO);
 int __read_mostly pi_inject_timer = -1;
 module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);
 
-#define KVM_NR_SHARED_MSRS 16
+/*
+ * Restoring the host value for MSRs that are only consumed when running in
+ * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
+ * returns to userspace, i.e. the kernel can run with the guest's value.
+ */
+#define KVM_MAX_NR_USER_RETURN_MSRS 16
 
-struct kvm_shared_msrs_global {
+struct kvm_user_return_msrs_global {
 	int nr;
-	u32 msrs[KVM_NR_SHARED_MSRS];
+	u32 msrs[KVM_MAX_NR_USER_RETURN_MSRS];
 };
 
-struct kvm_shared_msrs {
+struct kvm_user_return_msrs {
 	struct user_return_notifier urn;
 	bool registered;
-	struct kvm_shared_msr_values {
+	struct kvm_user_return_msr_values {
 		u64 host;
 		u64 curr;
-	} values[KVM_NR_SHARED_MSRS];
+	} values[KVM_MAX_NR_USER_RETURN_MSRS];
 };
 
-static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
-static struct kvm_shared_msrs __percpu *shared_msrs;
+static struct kvm_user_return_msrs_global __read_mostly user_return_msrs_global;
+static struct kvm_user_return_msrs __percpu *user_return_msrs;
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
 				| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
@@ -266,7 +272,7 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
 	} else {
 		vcpu_debug_ratelimited(vcpu, "unhandled %s: 0x%x data 0x%llx\n",
 				       op, msr, data);
-		return 1;
+		return -ENOENT;
 	}
 }
 
@@ -293,9 +299,9 @@ static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
 static void kvm_on_user_return(struct user_return_notifier *urn)
 {
 	unsigned slot;
-	struct kvm_shared_msrs *locals
-		= container_of(urn, struct kvm_shared_msrs, urn);
-	struct kvm_shared_msr_values *values;
+	struct kvm_user_return_msrs *msrs
+		= container_of(urn, struct kvm_user_return_msrs, urn);
+	struct kvm_user_return_msr_values *values;
 	unsigned long flags;
 
 	/*
@@ -303,73 +309,73 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	 * interrupted and executed through kvm_arch_hardware_disable()
 	 */
 	local_irq_save(flags);
-	if (locals->registered) {
-		locals->registered = false;
+	if (msrs->registered) {
+		msrs->registered = false;
 		user_return_notifier_unregister(urn);
 	}
 	local_irq_restore(flags);
-	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
-		values = &locals->values[slot];
+	for (slot = 0; slot < user_return_msrs_global.nr; ++slot) {
+		values = &msrs->values[slot];
 		if (values->host != values->curr) {
-			wrmsrl(shared_msrs_global.msrs[slot], values->host);
+			wrmsrl(user_return_msrs_global.msrs[slot], values->host);
 			values->curr = values->host;
 		}
 	}
 }
 
-void kvm_define_shared_msr(unsigned slot, u32 msr)
+void kvm_define_user_return_msr(unsigned slot, u32 msr)
 {
-	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
-	shared_msrs_global.msrs[slot] = msr;
-	if (slot >= shared_msrs_global.nr)
-		shared_msrs_global.nr = slot + 1;
+	BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS);
+	user_return_msrs_global.msrs[slot] = msr;
+	if (slot >= user_return_msrs_global.nr)
+		user_return_msrs_global.nr = slot + 1;
 }
-EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
+EXPORT_SYMBOL_GPL(kvm_define_user_return_msr);
 
-static void kvm_shared_msr_cpu_online(void)
+static void kvm_user_return_msr_cpu_online(void)
 {
 	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
 	u64 value;
 	int 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;
+	for (i = 0; i < user_return_msrs_global.nr; ++i) {
+		rdmsrl_safe(user_return_msrs_global.msrs[i], &value);
+		msrs->values[i].host = value;
+		msrs->values[i].curr = value;
 	}
 }
 
-int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
 {
 	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
 	int err;
 
-	value = (value & mask) | (smsr->values[slot].host & ~mask);
-	if (value == smsr->values[slot].curr)
+	value = (value & mask) | (msrs->values[slot].host & ~mask);
+	if (value == msrs->values[slot].curr)
 		return 0;
-	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
+	err = wrmsrl_safe(user_return_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);
-		smsr->registered = true;
+	msrs->values[slot].curr = value;
+	if (!msrs->registered) {
+		msrs->urn.on_user_return = kvm_on_user_return;
+		user_return_notifier_register(&msrs->urn);
+		msrs->registered = true;
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
+EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);
 
 static void drop_user_return_notifiers(void)
 {
 	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
 
-	if (smsr->registered)
-		kvm_on_user_return(&smsr->urn);
+	if (msrs->registered)
+		kvm_on_user_return(&msrs->urn);
 }
 
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
@@ -1452,6 +1458,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	u64 old_efer = vcpu->arch.efer;
 	u64 efer = msr_info->data;
+	int r;
 
 	if (efer & efer_reserved_bits)
 		return 1;
@@ -1468,7 +1475,11 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	efer &= ~EFER_LMA;
 	efer |= vcpu->arch.efer & EFER_LMA;
 
-	kvm_x86_ops.set_efer(vcpu, efer);
+	r = kvm_x86_ops.set_efer(vcpu, efer);
+	if (r) {
+		WARN_ON(r > 0);
+		return r;
+	}
 
 	/* Update reserved bits */
 	if ((efer ^ old_efer) & EFER_NX)
@@ -1483,6 +1494,40 @@ void kvm_enable_efer_bits(u64 mask)
 }
 EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
 
+bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
+	u32 count = kvm->arch.msr_filter.count;
+	u32 i;
+	bool r = kvm->arch.msr_filter.default_allow;
+	int idx;
+
+	/* MSR filtering not set up or x2APIC enabled, allow everything */
+	if (!count || (index >= 0x800 && index <= 0x8ff))
+		return true;
+
+	/* Prevent collision with set_msr_filter */
+	idx = srcu_read_lock(&kvm->srcu);
+
+	for (i = 0; i < count; i++) {
+		u32 start = ranges[i].base;
+		u32 end = start + ranges[i].nmsrs;
+		u32 flags = ranges[i].flags;
+		unsigned long *bitmap = ranges[i].bitmap;
+
+		if ((index >= start) && (index < end) && (flags & type)) {
+			r = !!test_bit(index - start, bitmap);
+			break;
+		}
+	}
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_msr_allowed);
+
 /*
  * Write @data into the MSR specified by @index.  Select MSR specific fault
  * checks are bypassed if @host_initiated is %true.
@@ -1494,6 +1539,9 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
 {
 	struct msr_data msr;
 
+	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
+		return -EPERM;
+
 	switch (index) {
 	case MSR_FS_BASE:
 	case MSR_GS_BASE:
@@ -1550,6 +1598,9 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
 	struct msr_data msr;
 	int ret;
 
+	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
+		return -EPERM;
+
 	msr.index = index;
 	msr.host_initiated = host_initiated;
 
@@ -1585,12 +1636,91 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 }
 EXPORT_SYMBOL_GPL(kvm_set_msr);
 
+static int complete_emulated_msr(struct kvm_vcpu *vcpu, bool is_read)
+{
+	if (vcpu->run->msr.error) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	} else if (is_read) {
+		kvm_rax_write(vcpu, (u32)vcpu->run->msr.data);
+		kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32);
+	}
+
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
+{
+	return complete_emulated_msr(vcpu, true);
+}
+
+static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu)
+{
+	return complete_emulated_msr(vcpu, false);
+}
+
+static u64 kvm_msr_reason(int r)
+{
+	switch (r) {
+	case -ENOENT:
+		return KVM_MSR_EXIT_REASON_UNKNOWN;
+	case -EPERM:
+		return KVM_MSR_EXIT_REASON_FILTER;
+	default:
+		return KVM_MSR_EXIT_REASON_INVAL;
+	}
+}
+
+static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index,
+			      u32 exit_reason, u64 data,
+			      int (*completion)(struct kvm_vcpu *vcpu),
+			      int r)
+{
+	u64 msr_reason = kvm_msr_reason(r);
+
+	/* Check if the user wanted to know about this MSR fault */
+	if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason))
+		return 0;
+
+	vcpu->run->exit_reason = exit_reason;
+	vcpu->run->msr.error = 0;
+	memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad));
+	vcpu->run->msr.reason = msr_reason;
+	vcpu->run->msr.index = index;
+	vcpu->run->msr.data = data;
+	vcpu->arch.complete_userspace_io = completion;
+
+	return 1;
+}
+
+static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r)
+{
+	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0,
+				   complete_emulated_rdmsr, r);
+}
+
+static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r)
+{
+	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data,
+				   complete_emulated_wrmsr, r);
+}
+
 int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data;
+	int r;
+
+	r = kvm_get_msr(vcpu, ecx, &data);
 
-	if (kvm_get_msr(vcpu, ecx, &data)) {
+	/* MSR read failed? See if we should ask user space */
+	if (r && kvm_get_msr_user_space(vcpu, ecx, r)) {
+		/* Bounce to user space */
+		return 0;
+	}
+
+	/* MSR read failed? Inject a #GP */
+	if (r) {
 		trace_kvm_msr_read_ex(ecx);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -1608,8 +1738,21 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data = kvm_read_edx_eax(vcpu);
+	int r;
 
-	if (kvm_set_msr(vcpu, ecx, data)) {
+	r = kvm_set_msr(vcpu, ecx, data);
+
+	/* MSR write failed? See if we should ask user space */
+	if (r && kvm_set_msr_user_space(vcpu, ecx, data, r))
+		/* Bounce to user space */
+		return 0;
+
+	/* Signal all other negative errors to userspace */
+	if (r < 0)
+		return r;
+
+	/* MSR write failed? Inject a #GP */
+	if (r > 0) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -1775,12 +1918,6 @@ static s64 get_kvmclock_base_ns(void)
 }
 #endif
 
-void kvm_set_pending_timer(struct kvm_vcpu *vcpu)
-{
-	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
-	kvm_vcpu_kick(vcpu);
-}
-
 static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 {
 	int version;
@@ -1788,6 +1925,8 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	struct pvclock_wall_clock wc;
 	u64 wall_nsec;
 
+	kvm->arch.wall_clock = wall_clock;
+
 	if (!wall_clock)
 		return;
 
@@ -1820,6 +1959,34 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
 }
 
+static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
+				  bool old_msr, bool host_initiated)
+{
+	struct kvm_arch *ka = &vcpu->kvm->arch;
+
+	if (vcpu->vcpu_id == 0 && !host_initiated) {
+		if (ka->boot_vcpu_runs_old_kvmclock && old_msr)
+			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
+
+		ka->boot_vcpu_runs_old_kvmclock = old_msr;
+	}
+
+	vcpu->arch.time = system_time;
+	kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
+
+	/* we verify if the enable bit is set... */
+	vcpu->arch.pv_time_enabled = false;
+	if (!(system_time & 1))
+		return;
+
+	if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
+				       &vcpu->arch.pv_time, system_time & ~1ULL,
+				       sizeof(struct pvclock_vcpu_time_info)))
+		vcpu->arch.pv_time_enabled = true;
+
+	return;
+}
+
 static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
 {
 	do_shl32_div32(dividend, divisor);
@@ -1979,12 +2146,6 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 #endif
 }
 
-static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
-{
-	u64 curr_offset = vcpu->arch.l1_tsc_offset;
-	vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
-}
-
 /*
  * Multiply tsc by a fixed point number represented by ratio.
  *
@@ -2046,14 +2207,13 @@ static inline bool kvm_check_tsc_unstable(void)
 	return check_tsc_unstable();
 }
 
-void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
+static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm *kvm = vcpu->kvm;
 	u64 offset, ns, elapsed;
 	unsigned long flags;
 	bool matched;
 	bool already_matched;
-	u64 data = msr->data;
 	bool synchronizing = false;
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
@@ -2062,7 +2222,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
-		if (data == 0 && msr->host_initiated) {
+		if (data == 0) {
 			/*
 			 * detection of vcpu initialization -- need to sync
 			 * with other vCPUs. This particularly helps to keep
@@ -2132,9 +2292,6 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
 	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
 
-	if (!msr->host_initiated && guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST))
-		update_ia32_tsc_adjust_msr(vcpu, offset);
-
 	kvm_vcpu_write_tsc_offset(vcpu, offset);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
@@ -2149,8 +2306,6 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
 }
 
-EXPORT_SYMBOL_GPL(kvm_write_tsc);
-
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
 					   s64 adjustment)
 {
@@ -2696,24 +2851,19 @@ static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
 	u32 page_num = data & ~PAGE_MASK;
 	u64 page_addr = data & PAGE_MASK;
 	u8 *page;
-	int r;
 
-	r = -E2BIG;
 	if (page_num >= blob_size)
-		goto out;
-	r = -ENOMEM;
+		return 1;
+
 	page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE);
-	if (IS_ERR(page)) {
-		r = PTR_ERR(page);
-		goto out;
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
+	if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) {
+		kfree(page);
+		return 1;
 	}
-	if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE))
-		goto out_free;
-	r = 0;
-out_free:
-	kfree(page);
-out:
-	return r;
+	return 0;
 }
 
 static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu)
@@ -2731,6 +2881,14 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 	if (data & 0x30)
 		return 1;
 
+	if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_VMEXIT) &&
+	    (data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT))
+		return 1;
+
+	if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT) &&
+	    (data & KVM_ASYNC_PF_DELIVERY_AS_INT))
+		return 1;
+
 	if (!lapic_in_kernel(vcpu))
 		return data ? 1 : 0;
 
@@ -2808,10 +2966,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
-	trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
-		st->preempted & KVM_VCPU_FLUSH_TLB);
-	if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
-		kvm_vcpu_flush_tlb_guest(vcpu);
+	if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) {
+		trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
+				       st->preempted & KVM_VCPU_FLUSH_TLB);
+		if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
+			kvm_vcpu_flush_tlb_guest(vcpu);
+	}
 
 	vcpu->arch.st.preempted = 0;
 
@@ -2945,7 +3105,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.msr_ia32_power_ctl = data;
 		break;
 	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr_info);
+		if (msr_info->host_initiated) {
+			kvm_synchronize_tsc(vcpu, data);
+		} else {
+			u64 adj = kvm_compute_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset;
+			adjust_tsc_offset_guest(vcpu, adj);
+			vcpu->arch.ia32_tsc_adjust_msr += adj;
+		}
 		break;
 	case MSR_IA32_XSS:
 		if (!msr_info->host_initiated &&
@@ -2966,53 +3132,54 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.smi_count = data;
 		break;
 	case MSR_KVM_WALL_CLOCK_NEW:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+			return 1;
+
+		kvm_write_wall_clock(vcpu->kvm, data);
+		break;
 	case MSR_KVM_WALL_CLOCK:
-		vcpu->kvm->arch.wall_clock = data;
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+			return 1;
+
 		kvm_write_wall_clock(vcpu->kvm, data);
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
-	case MSR_KVM_SYSTEM_TIME: {
-		struct kvm_arch *ka = &vcpu->kvm->arch;
-
-		if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) {
-			bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
-
-			if (ka->boot_vcpu_runs_old_kvmclock != tmp)
-				kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
-
-			ka->boot_vcpu_runs_old_kvmclock = tmp;
-		}
-
-		vcpu->arch.time = data;
-		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 (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+			return 1;
 
-		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 = true;
+		kvm_write_system_time(vcpu, data, false, msr_info->host_initiated);
+		break;
+	case MSR_KVM_SYSTEM_TIME:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+			return 1;
 
+		kvm_write_system_time(vcpu, data, true,  msr_info->host_initiated);
 		break;
-	}
 	case MSR_KVM_ASYNC_PF_EN:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+			return 1;
+
 		if (kvm_pv_enable_async_pf(vcpu, data))
 			return 1;
 		break;
 	case MSR_KVM_ASYNC_PF_INT:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
+			return 1;
+
 		if (kvm_pv_enable_async_pf_int(vcpu, data))
 			return 1;
 		break;
 	case MSR_KVM_ASYNC_PF_ACK:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+			return 1;
 		if (data & 0x1) {
 			vcpu->arch.apf.pageready_pending = false;
 			kvm_check_async_pf_completion(vcpu);
 		}
 		break;
 	case MSR_KVM_STEAL_TIME:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME))
+			return 1;
 
 		if (unlikely(!sched_info_on()))
 			return 1;
@@ -3029,11 +3196,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		break;
 	case MSR_KVM_PV_EOI_EN:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
+			return 1;
+
 		if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8)))
 			return 1;
 		break;
 
 	case MSR_KVM_POLL_CONTROL:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL))
+			return 1;
+
 		/* only enable bit supported */
 		if (data & (-1ULL << 1))
 			return 1;
@@ -3229,7 +3402,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 * state this but appears to behave the same.
 		 *
 		 * On userspace reads and writes, however, we unconditionally
-		 * operate L1's TSC value to ensure backwards-compatible
+		 * return L1's TSC value to ensure backwards-compatible
 		 * behavior for migration.
 		 */
 		u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset :
@@ -3527,6 +3700,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_EXCEPTION_PAYLOAD:
 	case KVM_CAP_SET_GUEST_DEBUG:
 	case KVM_CAP_LAST_CPU:
+	case KVM_CAP_X86_USER_SPACE_MSR:
+	case KVM_CAP_X86_MSR_FILTER:
+	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -4397,6 +4573,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 
 		return kvm_x86_ops.enable_direct_tlbflush(vcpu);
 
+	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
+		vcpu->arch.pv_cpuid.enforce = cap->args[0];
+
+		return 0;
+
 	default:
 		return -EINVAL;
 	}
@@ -5047,6 +5228,10 @@ split_irqchip_unlock:
 		kvm->arch.exception_payload_enabled = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_X86_USER_SPACE_MSR:
+		kvm->arch.user_space_msr_mask = cap->args[0];
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -5054,6 +5239,110 @@ split_irqchip_unlock:
 	return r;
 }
 
+static void kvm_clear_msr_filter(struct kvm *kvm)
+{
+	u32 i;
+	u32 count = kvm->arch.msr_filter.count;
+	struct msr_bitmap_range ranges[16];
+
+	mutex_lock(&kvm->lock);
+	kvm->arch.msr_filter.count = 0;
+	memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0]));
+	mutex_unlock(&kvm->lock);
+	synchronize_srcu(&kvm->srcu);
+
+	for (i = 0; i < count; i++)
+		kfree(ranges[i].bitmap);
+}
+
+static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range)
+{
+	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
+	struct msr_bitmap_range range;
+	unsigned long *bitmap = NULL;
+	size_t bitmap_size;
+	int r;
+
+	if (!user_range->nmsrs)
+		return 0;
+
+	bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long);
+	if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE)
+		return -EINVAL;
+
+	bitmap = memdup_user((__user u8*)user_range->bitmap, bitmap_size);
+	if (IS_ERR(bitmap))
+		return PTR_ERR(bitmap);
+
+	range = (struct msr_bitmap_range) {
+		.flags = user_range->flags,
+		.base = user_range->base,
+		.nmsrs = user_range->nmsrs,
+		.bitmap = bitmap,
+	};
+
+	if (range.flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) {
+		r = -EINVAL;
+		goto err;
+	}
+
+	if (!range.flags) {
+		r = -EINVAL;
+		goto err;
+	}
+
+	/* Everything ok, add this range identifier to our global pool */
+	ranges[kvm->arch.msr_filter.count] = range;
+	/* Make sure we filled the array before we tell anyone to walk it */
+	smp_wmb();
+	kvm->arch.msr_filter.count++;
+
+	return 0;
+err:
+	kfree(bitmap);
+	return r;
+}
+
+static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_msr_filter __user *user_msr_filter = argp;
+	struct kvm_msr_filter filter;
+	bool default_allow;
+	int r = 0;
+	bool empty = true;
+	u32 i;
+
+	if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
+		return -EFAULT;
+
+	for (i = 0; i < ARRAY_SIZE(filter.ranges); i++)
+		empty &= !filter.ranges[i].nmsrs;
+
+	default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY);
+	if (empty && !default_allow)
+		return -EINVAL;
+
+	kvm_clear_msr_filter(kvm);
+
+	kvm->arch.msr_filter.default_allow = default_allow;
+
+	/*
+	 * Protect from concurrent calls to this function that could trigger
+	 * a TOCTOU violation on kvm->arch.msr_filter.count.
+	 */
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
+		r = kvm_add_msr_filter(kvm, &filter.ranges[i]);
+		if (r)
+			break;
+	}
+
+	kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
+	mutex_unlock(&kvm->lock);
+
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -5360,6 +5649,9 @@ set_pit2_out:
 	case KVM_SET_PMU_EVENT_FILTER:
 		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
 		break;
+	case KVM_X86_SET_MSR_FILTER:
+		r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
+		break;
 	default:
 		r = -ENOTTY;
 	}
@@ -5721,6 +6013,9 @@ int handle_ud(struct kvm_vcpu *vcpu)
 	char sig[5]; /* ud2; .ascii "kvm" */
 	struct x86_exception e;
 
+	if (unlikely(!kvm_x86_ops.can_emulate_instruction(vcpu, NULL, 0)))
+		return 1;
+
 	if (force_emulation_prefix &&
 	    kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu),
 				sig, sizeof(sig), &e) == 0 &&
@@ -6376,13 +6671,33 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
 static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 *pdata)
 {
-	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r;
+
+	r = kvm_get_msr(vcpu, msr_index, pdata);
+
+	if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) {
+		/* Bounce to user space */
+		return X86EMUL_IO_NEEDED;
+	}
+
+	return r;
 }
 
 static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 data)
 {
-	return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r;
+
+	r = kvm_set_msr(vcpu, msr_index, data);
+
+	if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) {
+		/* Bounce to user space */
+		return X86EMUL_IO_NEEDED;
+	}
+
+	return r;
 }
 
 static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
@@ -6926,7 +7241,10 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	int r;
 	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
 	bool writeback = true;
-	bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
+	bool write_fault_to_spt;
+
+	if (unlikely(!kvm_x86_ops.can_emulate_instruction(vcpu, insn, insn_len)))
+		return 1;
 
 	vcpu->arch.l1tf_flush_l1d = true;
 
@@ -6934,6 +7252,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	 * Clear write_fault_to_shadow_pgtable here to ensure it is
 	 * never reused.
 	 */
+	write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 	vcpu->arch.write_fault_to_shadow_pgtable = false;
 	kvm_clear_exception_queue(vcpu);
 
@@ -7528,9 +7847,9 @@ int kvm_arch_init(void *opaque)
 		goto out_free_x86_fpu_cache;
 	}
 
-	shared_msrs = alloc_percpu(struct kvm_shared_msrs);
-	if (!shared_msrs) {
-		printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n");
+	user_return_msrs = alloc_percpu(struct kvm_user_return_msrs);
+	if (!user_return_msrs) {
+		printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n");
 		goto out_free_x86_emulator_cache;
 	}
 
@@ -7563,7 +7882,7 @@ int kvm_arch_init(void *opaque)
 	return 0;
 
 out_free_percpu:
-	free_percpu(shared_msrs);
+	free_percpu(user_return_msrs);
 out_free_x86_emulator_cache:
 	kmem_cache_destroy(x86_emulator_cache);
 out_free_x86_fpu_cache:
@@ -7590,7 +7909,7 @@ void kvm_arch_exit(void)
 #endif
 	kvm_x86_ops.hardware_enable = NULL;
 	kvm_mmu_module_exit();
-	free_percpu(shared_msrs);
+	free_percpu(user_return_msrs);
 	kmem_cache_destroy(x86_fpu_cache);
 }
 
@@ -7731,11 +8050,16 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
+	ret = -KVM_ENOSYS;
+
 	switch (nr) {
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
 	case KVM_HC_KICK_CPU:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_UNHALT))
+			break;
+
 		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
 		kvm_sched_yield(vcpu->kvm, a1);
 		ret = 0;
@@ -7746,9 +8070,15 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		break;
 #endif
 	case KVM_HC_SEND_IPI:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SEND_IPI))
+			break;
+
 		ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit);
 		break;
 	case KVM_HC_SCHED_YIELD:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED_YIELD))
+			break;
+
 		kvm_sched_yield(vcpu->kvm, a0);
 		ret = 0;
 		break;
@@ -8379,8 +8709,8 @@ 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)) {
-			if (unlikely(!kvm_x86_ops.nested_ops->get_vmcs12_pages(vcpu))) {
+		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
+			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
 				r = 0;
 				goto out;
 			}
@@ -8487,6 +8817,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_vcpu_update_apicv(vcpu);
 		if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
 			kvm_check_async_pf_completion(vcpu);
+		if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu))
+			kvm_x86_ops.msr_filter_changed(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -8562,7 +8894,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		kvm_x86_ops.request_immediate_exit(vcpu);
 	}
 
-	trace_kvm_entry(vcpu->vcpu_id);
+	trace_kvm_entry(vcpu);
 
 	fpregs_assert_state_consistent();
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
@@ -9576,7 +9908,6 @@ fail_mmu_destroy:
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
-	struct msr_data msr;
 	struct kvm *kvm = vcpu->kvm;
 
 	kvm_hv_vcpu_postcreate(vcpu);
@@ -9584,10 +9915,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	if (mutex_lock_killable(&vcpu->mutex))
 		return;
 	vcpu_load(vcpu);
-	msr.data = 0x0;
-	msr.index = MSR_IA32_TSC;
-	msr.host_initiated = true;
-	kvm_write_tsc(vcpu, &msr);
+	kvm_synchronize_tsc(vcpu, 0);
 	vcpu_put(vcpu);
 
 	/* poll control enabled by default */
@@ -9624,6 +9952,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_mmu_destroy(vcpu);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	free_page((unsigned long)vcpu->arch.pio_data);
+	kvfree(vcpu->arch.cpuid_entries);
 	if (!lapic_in_kernel(vcpu))
 		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
@@ -9721,7 +10050,7 @@ int kvm_arch_hardware_enable(void)
 	u64 max_tsc = 0;
 	bool stable, backwards_tsc = false;
 
-	kvm_shared_msr_cpu_online();
+	kvm_user_return_msr_cpu_online();
 	ret = kvm_x86_ops.hardware_enable();
 	if (ret != 0)
 		return ret;
@@ -10039,6 +10368,8 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
+	u32 i;
+
 	if (current->mm == kvm->mm) {
 		/*
 		 * Free memory regions allocated on behalf of userspace,
@@ -10055,6 +10386,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	}
 	if (kvm_x86_ops.vm_destroy)
 		kvm_x86_ops.vm_destroy(kvm);
+	for (i = 0; i < kvm->arch.msr_filter.count; i++)
+		kfree(kvm->arch.msr_filter.ranges[i].bitmap);
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
@@ -10785,6 +11118,111 @@ void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_c
 }
 EXPORT_SYMBOL_GPL(kvm_fixup_and_inject_pf_error);
 
+/*
+ * Handles kvm_read/write_guest_virt*() result and either injects #PF or returns
+ * KVM_EXIT_INTERNAL_ERROR for cases not currently handled by KVM. Return value
+ * indicates whether exit to userspace is needed.
+ */
+int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
+			      struct x86_exception *e)
+{
+	if (r == X86EMUL_PROPAGATE_FAULT) {
+		kvm_inject_emulated_page_fault(vcpu, e);
+		return 1;
+	}
+
+	/*
+	 * In case kvm_read/write_guest_virt*() failed with X86EMUL_IO_NEEDED
+	 * while handling a VMX instruction KVM could've handled the request
+	 * correctly by exiting to userspace and performing I/O but there
+	 * doesn't seem to be a real use-case behind such requests, just return
+	 * KVM_EXIT_INTERNAL_ERROR for now.
+	 */
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+	vcpu->run->internal.ndata = 0;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_handle_memory_failure);
+
+int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
+{
+	bool pcid_enabled;
+	struct x86_exception e;
+	unsigned i;
+	unsigned long roots_to_free = 0;
+	struct {
+		u64 pcid;
+		u64 gla;
+	} operand;
+	int r;
+
+	r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
+	if (r != X86EMUL_CONTINUE)
+		return kvm_handle_memory_failure(vcpu, r, &e);
+
+	if (operand.pcid >> 12 != 0) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+	switch (type) {
+	case INVPCID_TYPE_INDIV_ADDR:
+		if ((!pcid_enabled && (operand.pcid != 0)) ||
+		    is_noncanonical_address(operand.gla, vcpu)) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+		kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid);
+		return kvm_skip_emulated_instruction(vcpu);
+
+	case INVPCID_TYPE_SINGLE_CTXT:
+		if (!pcid_enabled && (operand.pcid != 0)) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+
+		if (kvm_get_active_pcid(vcpu) == operand.pcid) {
+			kvm_mmu_sync_roots(vcpu);
+			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+		}
+
+		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+			if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].pgd)
+			    == operand.pcid)
+				roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
+
+		kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
+		/*
+		 * If neither the current cr3 nor any of the prev_roots use the
+		 * given PCID, then nothing needs to be done here because a
+		 * resync will happen anyway before switching to any other CR3.
+		 */
+
+		return kvm_skip_emulated_instruction(vcpu);
+
+	case INVPCID_TYPE_ALL_NON_GLOBAL:
+		/*
+		 * Currently, KVM doesn't mark global entries in the shadow
+		 * page tables, so a non-global flush just degenerates to a
+		 * global flush. If needed, we could optimize this later by
+		 * keeping track of global entries in shadow page tables.
+		 */
+
+		fallthrough;
+	case INVPCID_TYPE_ALL_INCL_GLOBAL:
+		kvm_mmu_unload(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+
+	default:
+		BUG(); /* We have already checked above that type <= 3 */
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_handle_invpcid);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);