1 files changed, 190 insertions, 90 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 536b78c4af6e..58305cf81182 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Kernel-based Virtual Machine driver for Linux
  *
@@ -13,10 +14,6 @@
  *   Yaniv Kamay  <yaniv@qumranet.com>
  *   Amit Shah    <amit.shah@qumranet.com>
  *   Ben-Ami Yassour <benami@il.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #include <linux/kvm_host.h>
@@ -54,6 +51,7 @@
 #include <linux/kvm_irqfd.h>
 #include <linux/irqbypass.h>
 #include <linux/sched/stat.h>
+#include <linux/sched/isolation.h>
 #include <linux/mem_encrypt.h>
 
 #include <trace/events/kvm.h>
@@ -70,6 +68,7 @@
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/intel_pt.h>
+#include <clocksource/hyperv_timer.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -143,7 +142,7 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
  * tuning, i.e. allows priveleged userspace to set an exact advancement time.
  */
 static int __read_mostly lapic_timer_advance_ns = -1;
-module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR);
 
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
@@ -155,6 +154,9 @@ EXPORT_SYMBOL_GPL(enable_vmware_backdoor);
 static bool __read_mostly force_emulation_prefix = false;
 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
 
 struct kvm_shared_msrs_global {
@@ -719,7 +721,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int r;
 
-	if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
+	if (!is_pae_paging(vcpu))
 		return false;
 
 	if (!test_bit(VCPU_EXREG_PDPTR,
@@ -962,8 +964,8 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	if (is_long_mode(vcpu) &&
 	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
 		return 1;
-	else if (is_pae(vcpu) && is_paging(vcpu) &&
-		   !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
+	else if (is_pae_paging(vcpu) &&
+		 !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
 		return 1;
 
 	kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush);
@@ -1176,7 +1178,28 @@ static u32 emulated_msrs[] = {
 	MSR_AMD64_VIRT_SPEC_CTRL,
 	MSR_IA32_POWER_CTL,
 
+	/*
+	 * The following list leaves out MSRs whose values are determined
+	 * 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.
+	 */
+	MSR_IA32_VMX_BASIC,
+	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
+	MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
+	MSR_IA32_VMX_TRUE_EXIT_CTLS,
+	MSR_IA32_VMX_TRUE_ENTRY_CTLS,
+	MSR_IA32_VMX_MISC,
+	MSR_IA32_VMX_CR0_FIXED0,
+	MSR_IA32_VMX_CR4_FIXED0,
+	MSR_IA32_VMX_VMCS_ENUM,
+	MSR_IA32_VMX_PROCBASED_CTLS2,
+	MSR_IA32_VMX_EPT_VPID_CAP,
+	MSR_IA32_VMX_VMFUNC,
+
 	MSR_K7_HWCR,
+	MSR_KVM_POLL_CONTROL,
 };
 
 static unsigned num_emulated_msrs;
@@ -1212,11 +1235,12 @@ static u32 msr_based_features[] = {
 
 static unsigned int num_msr_based_features;
 
-u64 kvm_get_arch_capabilities(void)
+static u64 kvm_get_arch_capabilities(void)
 {
-	u64 data;
+	u64 data = 0;
 
-	rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
 
 	/*
 	 * If we're doing cache flushes (either "always" or "cond")
@@ -1232,7 +1256,6 @@ u64 kvm_get_arch_capabilities(void)
 
 	return data;
 }
-EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
 
 static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 {
@@ -1298,7 +1321,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	u64 efer = msr_info->data;
 
 	if (efer & efer_reserved_bits)
-		return false;
+		return 1;
 
 	if (!msr_info->host_initiated) {
 		if (!__kvm_valid_efer(vcpu, efer))
@@ -1437,12 +1460,8 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * Note: KVM_REQ_PENDING_TIMER is implicitly checked in
-	 * vcpu_enter_guest.  This function is only called from
-	 * the physical CPU that is running 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)
@@ -1521,9 +1540,6 @@ static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz,
 
 	*pshift = shift;
 	*pmultiplier = div_frac(scaled64, tps32);
-
-	pr_debug("%s: base_hz %llu => %llu, shift %d, mul %u\n",
-		 __func__, base_hz, scaled_hz, shift, *pmultiplier);
 }
 
 #ifdef CONFIG_X86_64
@@ -1557,7 +1573,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 			vcpu->arch.tsc_always_catchup = 1;
 			return 0;
 		} else {
-			WARN(1, "user requested TSC rate below hardware speed\n");
+			pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
 			return -1;
 		}
 	}
@@ -1567,8 +1583,8 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 				user_tsc_khz, tsc_khz);
 
 	if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
-		WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
-			  user_tsc_khz);
+		pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
+			            user_tsc_khz);
 		return -1;
 	}
 
@@ -1731,7 +1747,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
 	offset = kvm_compute_tsc_offset(vcpu, data);
-	ns = ktime_get_boot_ns();
+	ns = ktime_get_boottime_ns();
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
@@ -1766,12 +1782,10 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	    vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
 		if (!kvm_check_tsc_unstable()) {
 			offset = kvm->arch.cur_tsc_offset;
-			pr_debug("kvm: matched tsc offset for %llu\n", data);
 		} else {
 			u64 delta = nsec_to_cycles(vcpu, elapsed);
 			data += delta;
 			offset = kvm_compute_tsc_offset(vcpu, data);
-			pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
 		}
 		matched = true;
 		already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation);
@@ -1790,8 +1804,6 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		kvm->arch.cur_tsc_write = data;
 		kvm->arch.cur_tsc_offset = offset;
 		matched = false;
-		pr_debug("kvm: new tsc generation %llu, clock %llu\n",
-			 kvm->arch.cur_tsc_generation, data);
 	}
 
 	/*
@@ -2073,7 +2085,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	if (!ka->use_master_clock) {
 		spin_unlock(&ka->pvclock_gtod_sync_lock);
-		return ktime_get_boot_ns() + ka->kvmclock_offset;
+		return ktime_get_boottime_ns() + ka->kvmclock_offset;
 	}
 
 	hv_clock.tsc_timestamp = ka->master_cycle_now;
@@ -2089,7 +2101,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 				   &hv_clock.tsc_to_system_mul);
 		ret = __pvclock_read_cycles(&hv_clock, rdtsc());
 	} else
-		ret = ktime_get_boot_ns() + ka->kvmclock_offset;
+		ret = ktime_get_boottime_ns() + ka->kvmclock_offset;
 
 	put_cpu();
 
@@ -2188,7 +2200,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	}
 	if (!use_master_clock) {
 		host_tsc = rdtsc();
-		kernel_ns = ktime_get_boot_ns();
+		kernel_ns = ktime_get_boottime_ns();
 	}
 
 	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
@@ -2547,13 +2559,24 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		}
 		break;
 	case MSR_IA32_MISC_ENABLE:
-		vcpu->arch.ia32_misc_enable_msr = data;
+		if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) &&
+		    ((vcpu->arch.ia32_misc_enable_msr ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) {
+			if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3))
+				return 1;
+			vcpu->arch.ia32_misc_enable_msr = data;
+			kvm_update_cpuid(vcpu);
+		} else {
+			vcpu->arch.ia32_misc_enable_msr = data;
+		}
 		break;
 	case MSR_IA32_SMBASE:
 		if (!msr_info->host_initiated)
 			return 1;
 		vcpu->arch.smbase = data;
 		break;
+	case MSR_IA32_POWER_CTL:
+		vcpu->arch.msr_ia32_power_ctl = data;
+		break;
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
@@ -2628,6 +2651,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		break;
 
+	case MSR_KVM_POLL_CONTROL:
+		/* only enable bit supported */
+		if (data & (-1ULL << 1))
+			return 1;
+
+		vcpu->arch.msr_kvm_poll_control = data;
+		break;
+
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
@@ -2805,6 +2836,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		msr_info->data = vcpu->arch.arch_capabilities;
 		break;
+	case MSR_IA32_POWER_CTL:
+		msr_info->data = vcpu->arch.msr_ia32_power_ctl;
+		break;
 	case MSR_IA32_TSC:
 		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
 		break;
@@ -2877,6 +2911,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_KVM_PV_EOI_EN:
 		msr_info->data = vcpu->arch.pv_eoi.msr_val;
 		break;
+	case MSR_KVM_POLL_CONTROL:
+		msr_info->data = vcpu->arch.msr_kvm_poll_control;
+		break;
 	case MSR_IA32_P5_MC_ADDR:
 	case MSR_IA32_P5_MC_TYPE:
 	case MSR_IA32_MCG_CAP:
@@ -3086,6 +3123,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SET_BOOT_CPU_ID:
  	case KVM_CAP_SPLIT_IRQCHIP:
 	case KVM_CAP_IMMEDIATE_EXIT:
+	case KVM_CAP_PMU_EVENT_FILTER:
 	case KVM_CAP_GET_MSR_FEATURES:
 	case KVM_CAP_MSR_PLATFORM_INFO:
 	case KVM_CAP_EXCEPTION_PAYLOAD:
@@ -3098,7 +3136,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_CLOCK_TSC_STABLE;
 		break;
 	case KVM_CAP_X86_DISABLE_EXITS:
-		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE;
+		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
+		      KVM_X86_DISABLE_EXITS_CSTATE;
 		if(kvm_can_mwait_in_guest())
 			r |= KVM_X86_DISABLE_EXITS_MWAIT;
 		break;
@@ -3122,6 +3161,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+	case KVM_CAP_MAX_VCPU_ID:
+		r = KVM_MAX_VCPU_ID;
+		break;
 	case KVM_CAP_PV_MMU:	/* obsolete */
 		r = 0;
 		break;
@@ -4612,6 +4654,8 @@ split_irqchip_unlock:
 			kvm->arch.hlt_in_guest = true;
 		if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
 			kvm->arch.pause_in_guest = true;
+		if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
+			kvm->arch.cstate_in_guest = true;
 		r = 0;
 		break;
 	case KVM_CAP_MSR_PLATFORM_INFO:
@@ -4926,6 +4970,9 @@ set_identity_unlock:
 		r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd);
 		break;
 	}
+	case KVM_SET_PMU_EVENT_FILTER:
+		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
+		break;
 	default:
 		r = -ENOTTY;
 	}
@@ -6378,7 +6425,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
 					   vcpu->arch.db);
 
 		if (dr6 != 0) {
-			vcpu->arch.dr6 &= ~15;
+			vcpu->arch.dr6 &= ~DR_TRAP_BITS;
 			vcpu->arch.dr6 |= dr6 | DR6_RTM;
 			kvm_queue_exception(vcpu, DB_VECTOR);
 			*r = EMULATE_DONE;
@@ -6705,7 +6752,7 @@ static void kvm_hyperv_tsc_notifier(void)
 	struct kvm_vcpu *vcpu;
 	int cpu;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_make_mclock_inprogress_request(kvm);
 
@@ -6731,7 +6778,7 @@ static void kvm_hyperv_tsc_notifier(void)
 
 		spin_unlock(&ka->pvclock_gtod_sync_lock);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 }
 #endif
 
@@ -6782,17 +6829,17 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu)
 
 	smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != cpu)
 				continue;
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
-			if (vcpu->cpu != smp_processor_id())
+			if (vcpu->cpu != raw_smp_processor_id())
 				send_ipi = 1;
 		}
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -6857,7 +6904,6 @@ static void kvm_timer_init(void)
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
 	}
-	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 
 	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
@@ -6907,35 +6953,6 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
 	.handle_intel_pt_intr	= kvm_handle_intel_pt_intr,
 };
 
-static void kvm_set_mmio_spte_mask(void)
-{
-	u64 mask;
-	int maxphyaddr = boot_cpu_data.x86_phys_bits;
-
-	/*
-	 * Set the reserved bits and the present bit of an paging-structure
-	 * entry to generate page fault with PFER.RSV = 1.
-	 */
-
-	/*
-	 * Mask the uppermost physical address bit, which would be reserved as
-	 * long as the supported physical address width is less than 52.
-	 */
-	mask = 1ull << 51;
-
-	/* Set the present bit. */
-	mask |= 1ull;
-
-	/*
-	 * If reserved bit is not supported, clear the present bit to disable
-	 * mmio page fault.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && maxphyaddr == 52)
-		mask &= ~1ull;
-
-	kvm_mmu_set_mmio_spte_mask(mask, mask);
-}
-
 #ifdef CONFIG_X86_64
 static void pvclock_gtod_update_fn(struct work_struct *work)
 {
@@ -6944,12 +6961,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 	atomic_set(&kvm_guest_has_master_clock, 0);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -7032,8 +7049,6 @@ int kvm_arch_init(void *opaque)
 	if (r)
 		goto out_free_percpu;
 
-	kvm_set_mmio_spte_mask();
-
 	kvm_x86_ops = ops;
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
@@ -7047,6 +7062,8 @@ int kvm_arch_init(void *opaque)
 		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 
 	kvm_lapic_init();
+	if (pi_inject_timer == -1)
+		pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER);
 #ifdef CONFIG_X86_64
 	pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
 
@@ -7172,6 +7189,23 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu);
 }
 
+static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id)
+{
+	struct kvm_vcpu *target = NULL;
+	struct kvm_apic_map *map;
+
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
+
+	if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id])
+		target = map->phys_map[dest_id]->vcpu;
+
+	rcu_read_unlock();
+
+	if (target)
+		kvm_vcpu_yield_to(target);
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
@@ -7218,6 +7252,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_SEND_IPI:
 		ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit);
 		break;
+	case KVM_HC_SCHED_YIELD:
+		kvm_sched_yield(vcpu->kvm, a0);
+		ret = 0;
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
@@ -7950,9 +7988,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
-	if (lapic_in_kernel(vcpu) &&
-	    vcpu->arch.apic->lapic_timer.timer_advance_ns)
-		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
 	fpregs_assert_state_consistent();
@@ -8001,13 +8036,29 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
-	kvm_before_interrupt(vcpu);
-	kvm_x86_ops->handle_external_intr(vcpu);
-	kvm_after_interrupt(vcpu);
+	kvm_x86_ops->handle_exit_irqoff(vcpu);
 
+	/*
+	 * Consume any pending interrupts, including the possible source of
+	 * VM-Exit on SVM and any ticks that occur between VM-Exit and now.
+	 * An instruction is required after local_irq_enable() to fully unblock
+	 * interrupts on processors that implement an interrupt shadow, the
+	 * stat.exits increment will do nicely.
+	 */
+	kvm_before_interrupt(vcpu);
+	local_irq_enable();
 	++vcpu->stat.exits;
+	local_irq_disable();
+	kvm_after_interrupt(vcpu);
 
 	guest_exit_irqoff();
+	if (lapic_in_kernel(vcpu)) {
+		s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta;
+		if (delta != S64_MIN) {
+			trace_kvm_wait_lapic_expire(vcpu->vcpu_id, delta);
+			vcpu->arch.apic->lapic_timer.advance_expire_delta = S64_MIN;
+		}
+	}
 
 	local_irq_enable();
 	preempt_enable();
@@ -8593,7 +8644,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		kvm_update_cpuid(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
+	if (is_pae_paging(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		mmu_reset_needed = 1;
 	}
@@ -8874,6 +8925,10 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	msr.host_initiated = true;
 	kvm_write_tsc(vcpu, &msr);
 	vcpu_put(vcpu);
+
+	/* poll control enabled by default */
+	vcpu->arch.msr_kvm_poll_control = 1;
+
 	mutex_unlock(&vcpu->mutex);
 
 	if (!kvmclock_periodic_sync)
@@ -9015,7 +9070,7 @@ int kvm_arch_hardware_enable(void)
 	 * before any KVM threads can be running.  Unfortunately, we can't
 	 * bring the TSCs fully up to date with real time, as we aren't yet far
 	 * enough into CPU bringup that we know how much real time has actually
-	 * elapsed; our helper function, ktime_get_boot_ns() will be using boot
+	 * elapsed; our helper function, ktime_get_boottime_ns() will be using boot
 	 * variables that haven't been updated yet.
 	 *
 	 * So we simply find the maximum observed TSC above, then record the
@@ -9106,9 +9161,9 @@ void kvm_arch_hardware_unsetup(void)
 	kvm_x86_ops->hardware_unsetup();
 }
 
-void kvm_arch_check_processor_compat(void *rtn)
+int kvm_arch_check_processor_compat(void)
 {
-	kvm_x86_ops->check_processor_compatibility(rtn);
+	return kvm_x86_ops->check_processor_compatibility();
 }
 
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
@@ -9243,7 +9298,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_init(&kvm->arch.apic_map_lock);
 	spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
 
-	kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
+	kvm->arch.kvmclock_offset = -ktime_get_boottime_ns();
 	pvclock_update_vm_gtod_copy(kvm);
 
 	kvm->arch.guest_can_read_msr_platform_info = true;
@@ -9380,6 +9435,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
 	kvm_page_track_cleanup(kvm);
 	kvm_hv_destroy_vm(kvm);
@@ -9788,6 +9844,36 @@ static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val)
 				      sizeof(u32));
 }
 
+static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
+		return false;
+
+	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) ||
+	    (vcpu->arch.apf.send_user_only &&
+	     kvm_x86_ops->get_cpl(vcpu) == 0))
+		return false;
+
+	return true;
+}
+
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(!lapic_in_kernel(vcpu) ||
+		     kvm_event_needs_reinjection(vcpu) ||
+		     vcpu->arch.exception.pending))
+		return false;
+
+	if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu))
+		return false;
+
+	/*
+	 * If interrupts are off we cannot even use an artificial
+	 * halt state.
+	 */
+	return kvm_x86_ops->interrupt_allowed(vcpu);
+}
+
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work)
 {
@@ -9796,11 +9882,8 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
-	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) ||
-	    (vcpu->arch.apf.send_user_only &&
-	     kvm_x86_ops->get_cpl(vcpu) == 0))
-		kvm_make_request(KVM_REQ_APF_HALT, vcpu);
-	else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) {
+	if (kvm_can_deliver_async_pf(vcpu) &&
+	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) {
 		fault.vector = PF_VECTOR;
 		fault.error_code_valid = true;
 		fault.error_code = 0;
@@ -9808,6 +9891,16 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 		fault.address = work->arch.token;
 		fault.async_page_fault = true;
 		kvm_inject_page_fault(vcpu, &fault);
+	} else {
+		/*
+		 * It is not possible to deliver a paravirtualized asynchronous
+		 * page fault, but putting the guest in an artificial halt state
+		 * can be beneficial nevertheless: if an interrupt arrives, we
+		 * can deliver it timely and perhaps the guest will schedule
+		 * another process.  When the instruction that triggered a page
+		 * fault is retried, hopefully the page will be ready in the host.
+		 */
+		kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 	}
 }
 
@@ -9948,6 +10041,13 @@ bool kvm_vector_hashing_enabled(void)
 }
 EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
 
+bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.msr_kvm_poll_control & 1) == 0;
+}
+EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
+
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);