Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM64:

   - Enable the per-vcpu dirty-ring tracking mechanism, together with an
     option to keep the good old dirty log around for pages that are
     dirtied by something other than a vcpu.

   - Switch to the relaxed parallel fault handling, using RCU to delay
     page table reclaim and giving better performance under load.

   - Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping
     option, which multi-process VMMs such as crosvm rely on (see merge
     commit 382b5b87a97d: "Fix a number of issues with MTE, such as
     races on the tags being initialised vs the PG_mte_tagged flag as
     well as the lack of support for VM_SHARED when KVM is involved.
     Patches from Catalin Marinas and Peter Collingbourne").

   - Merge the pKVM shadow vcpu state tracking that allows the
     hypervisor to have its own view of a vcpu, keeping that state
     private.

   - Add support for the PMUv3p5 architecture revision, bringing support
     for 64bit counters on systems that support it, and fix the
     no-quite-compliant CHAIN-ed counter support for the machines that
     actually exist out there.

   - Fix a handful of minor issues around 52bit VA/PA support (64kB
     pages only) as a prefix of the oncoming support for 4kB and 16kB
     pages.

   - Pick a small set of documentation and spelling fixes, because no
     good merge window would be complete without those.

  s390:

   - Second batch of the lazy destroy patches

   - First batch of KVM changes for kernel virtual != physical address
     support

   - Removal of a unused function

  x86:

   - Allow compiling out SMM support

   - Cleanup and documentation of SMM state save area format

   - Preserve interrupt shadow in SMM state save area

   - Respond to generic signals during slow page faults

   - Fixes and optimizations for the non-executable huge page errata
     fix.

   - Reprogram all performance counters on PMU filter change

   - Cleanups to Hyper-V emulation and tests

   - Process Hyper-V TLB flushes from a nested guest (i.e. from a L2
     guest running on top of a L1 Hyper-V hypervisor)

   - Advertise several new Intel features

   - x86 Xen-for-KVM:

      - Allow the Xen runstate information to cross a page boundary

      - Allow XEN_RUNSTATE_UPDATE flag behaviour to be configured

      - Add support for 32-bit guests in SCHEDOP_poll

   - Notable x86 fixes and cleanups:

      - One-off fixes for various emulation flows (SGX, VMXON, NRIPS=0).

      - Reinstate IBPB on emulated VM-Exit that was incorrectly dropped
        a few years back when eliminating unnecessary barriers when
        switching between vmcs01 and vmcs02.

      - Clean up vmread_error_trampoline() to make it more obvious that
        params must be passed on the stack, even for x86-64.

      - Let userspace set all supported bits in MSR_IA32_FEAT_CTL
        irrespective of the current guest CPUID.

      - Fudge around a race with TSC refinement that results in KVM
        incorrectly thinking a guest needs TSC scaling when running on a
        CPU with a constant TSC, but no hardware-enumerated TSC
        frequency.

      - Advertise (on AMD) that the SMM_CTL MSR is not supported

      - Remove unnecessary exports

  Generic:

   - Support for responding to signals during page faults; introduces
     new FOLL_INTERRUPTIBLE flag that was reviewed by mm folks

  Selftests:

   - Fix an inverted check in the access tracking perf test, and restore
     support for asserting that there aren't too many idle pages when
     running on bare metal.

   - Fix build errors that occur in certain setups (unsure exactly what
     is unique about the problematic setup) due to glibc overriding
     static_assert() to a variant that requires a custom message.

   - Introduce actual atomics for clear/set_bit() in selftests

   - Add support for pinning vCPUs in dirty_log_perf_test.

   - Rename the so called "perf_util" framework to "memstress".

   - Add a lightweight psuedo RNG for guest use, and use it to randomize
     the access pattern and write vs. read percentage in the memstress
     tests.

   - Add a common ucall implementation; code dedup and pre-work for
     running SEV (and beyond) guests in selftests.

   - Provide a common constructor and arch hook, which will eventually
     be used by x86 to automatically select the right hypercall (AMD vs.
     Intel).

   - A bunch of added/enabled/fixed selftests for ARM64, covering
     memslots, breakpoints, stage-2 faults and access tracking.

   - x86-specific selftest changes:

      - Clean up x86's page table management.

      - Clean up and enhance the "smaller maxphyaddr" test, and add a
        related test to cover generic emulation failure.

      - Clean up the nEPT support checks.

      - Add X86_PROPERTY_* framework to retrieve multi-bit CPUID values.

      - Fix an ordering issue in the AMX test introduced by recent
        conversions to use kvm_cpu_has(), and harden the code to guard
        against similar bugs in the future. Anything that tiggers
        caching of KVM's supported CPUID, kvm_cpu_has() in this case,
        effectively hides opt-in XSAVE features if the caching occurs
        before the test opts in via prctl().

  Documentation:

   - Remove deleted ioctls from documentation

   - Clean up the docs for the x86 MSR filter.

   - Various fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (361 commits)
  KVM: x86: Add proper ReST tables for userspace MSR exits/flags
  KVM: selftests: Allocate ucall pool from MEM_REGION_DATA
  KVM: arm64: selftests: Align VA space allocator with TTBR0
  KVM: arm64: Fix benign bug with incorrect use of VA_BITS
  KVM: arm64: PMU: Fix period computation for 64bit counters with 32bit overflow
  KVM: x86: Advertise that the SMM_CTL MSR is not supported
  KVM: x86: remove unnecessary exports
  KVM: selftests: Fix spelling mistake "probabalistic" -> "probabilistic"
  tools: KVM: selftests: Convert clear/set_bit() to actual atomics
  tools: Drop "atomic_" prefix from atomic test_and_set_bit()
  tools: Drop conflicting non-atomic test_and_{clear,set}_bit() helpers
  KVM: selftests: Use non-atomic clear/set bit helpers in KVM tests
  perf tools: Use dedicated non-atomic clear/set bit helpers
  tools: Take @bit as an "unsigned long" in {clear,set}_bit() helpers
  KVM: arm64: selftests: Enable single-step without a "full" ucall()
  KVM: x86: fix APICv/x2AVIC disabled when vm reboot by itself
  KVM: Remove stale comment about KVM_REQ_UNHALT
  KVM: Add missing arch for KVM_CREATE_DEVICE and KVM_{SET,GET}_DEVICE_ATTR
  KVM: Reference to kvm_userspace_memory_region in doc and comments
  KVM: Delete all references to removed KVM_SET_MEMORY_ALIAS ioctl
  ...

1 files changed, 128 insertions, 405 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 69227f77b201..312aea1854ae 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -30,6 +30,7 @@
 #include "hyperv.h"
 #include "lapic.h"
 #include "xen.h"
+#include "smm.h"
 
 #include <linux/clocksource.h>
 #include <linux/interrupt.h>
@@ -119,8 +120,6 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
-static void process_smi(struct kvm_vcpu *vcpu);
-static void enter_smm(struct kvm_vcpu *vcpu);
 static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 static void store_regs(struct kvm_vcpu *vcpu);
 static int sync_regs(struct kvm_vcpu *vcpu);
@@ -464,7 +463,6 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.apic_base;
 }
-EXPORT_SYMBOL_GPL(kvm_get_apic_base);
 
 enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
 {
@@ -492,7 +490,6 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	kvm_recalculate_apic_map(vcpu->kvm);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 
 /*
  * Handle a fault on a hardware virtualization (VMX or SVM) instruction.
@@ -783,7 +780,6 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 		kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code,
 					fault->address);
 }
-EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
 
 void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
 				    struct x86_exception *fault)
@@ -812,7 +808,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu)
 	atomic_inc(&vcpu->arch.nmi_queued);
 	kvm_make_request(KVM_REQ_NMI, vcpu);
 }
-EXPORT_SYMBOL_GPL(kvm_inject_nmi);
 
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
 {
@@ -837,7 +832,6 @@ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl)
 	kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
 	return false;
 }
-EXPORT_SYMBOL_GPL(kvm_require_cpl);
 
 bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr)
 {
@@ -1654,6 +1648,9 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 	case MSR_IA32_ARCH_CAPABILITIES:
 		msr->data = kvm_get_arch_capabilities();
 		break;
+	case MSR_IA32_PERF_CAPABILITIES:
+		msr->data = kvm_caps.supported_perf_cap;
+		break;
 	case MSR_IA32_UCODE_REV:
 		rdmsrl_safe(msr->index, &msr->data);
 		break;
@@ -2067,7 +2064,6 @@ int kvm_emulate_as_nop(struct kvm_vcpu *vcpu)
 {
 	return kvm_skip_emulated_instruction(vcpu);
 }
-EXPORT_SYMBOL_GPL(kvm_emulate_as_nop);
 
 int kvm_emulate_invd(struct kvm_vcpu *vcpu)
 {
@@ -2315,13 +2311,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
 	kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
 	/* we verify if the enable bit is set... */
-	if (system_time & 1) {
-		kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
-				 KVM_HOST_USES_PFN, system_time & ~1ULL,
+	if (system_time & 1)
+		kvm_gpc_activate(&vcpu->arch.pv_time, system_time & ~1ULL,
 				 sizeof(struct pvclock_vcpu_time_info));
-	} else {
-		kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
-	}
+	else
+		kvm_gpc_deactivate(&vcpu->arch.pv_time);
 
 	return;
 }
@@ -2513,7 +2507,6 @@ u64 kvm_scale_tsc(u64 tsc, u64 ratio)
 
 	return _tsc;
 }
-EXPORT_SYMBOL_GPL(kvm_scale_tsc);
 
 static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 {
@@ -2972,6 +2965,22 @@ static void kvm_update_masterclock(struct kvm *kvm)
 	kvm_end_pvclock_update(kvm);
 }
 
+/*
+ * Use the kernel's tsc_khz directly if the TSC is constant, otherwise use KVM's
+ * per-CPU value (which may be zero if a CPU is going offline).  Note, tsc_khz
+ * can change during boot even if the TSC is constant, as it's possible for KVM
+ * to be loaded before TSC calibration completes.  Ideally, KVM would get a
+ * notification when calibration completes, but practically speaking calibration
+ * will complete before userspace is alive enough to create VMs.
+ */
+static unsigned long get_cpu_tsc_khz(void)
+{
+	if (static_cpu_has(X86_FEATURE_CONSTANT_TSC))
+		return tsc_khz;
+	else
+		return __this_cpu_read(cpu_tsc_khz);
+}
+
 /* Called within read_seqcount_begin/retry for kvm->pvclock_sc.  */
 static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
 {
@@ -2982,7 +2991,8 @@ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
 	get_cpu();
 
 	data->flags = 0;
-	if (ka->use_master_clock && __this_cpu_read(cpu_tsc_khz)) {
+	if (ka->use_master_clock &&
+	    (static_cpu_has(X86_FEATURE_CONSTANT_TSC) || __this_cpu_read(cpu_tsc_khz))) {
 #ifdef CONFIG_X86_64
 		struct timespec64 ts;
 
@@ -2996,7 +3006,7 @@ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
 		data->flags |= KVM_CLOCK_TSC_STABLE;
 		hv_clock.tsc_timestamp = ka->master_cycle_now;
 		hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
-		kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+		kvm_get_time_scale(NSEC_PER_SEC, get_cpu_tsc_khz() * 1000LL,
 				   &hv_clock.tsc_shift,
 				   &hv_clock.tsc_to_system_mul);
 		data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc);
@@ -3035,12 +3045,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 	unsigned long flags;
 
 	read_lock_irqsave(&gpc->lock, flags);
-	while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa,
-					   offset + sizeof(*guest_hv_clock))) {
+	while (!kvm_gpc_check(gpc, offset + sizeof(*guest_hv_clock))) {
 		read_unlock_irqrestore(&gpc->lock, flags);
 
-		if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa,
-						 offset + sizeof(*guest_hv_clock)))
+		if (kvm_gpc_refresh(gpc, offset + sizeof(*guest_hv_clock)))
 			return;
 
 		read_lock_irqsave(&gpc->lock, flags);
@@ -3106,7 +3114,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
-	tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
+	tgt_tsc_khz = get_cpu_tsc_khz();
 	if (unlikely(tgt_tsc_khz == 0)) {
 		local_irq_restore(flags);
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
@@ -3389,7 +3397,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-	kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
+	kvm_gpc_deactivate(&vcpu->arch.pv_time);
 	vcpu->arch.time = 0;
 }
 
@@ -3397,6 +3405,9 @@ static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.tlb_flush;
 	static_call(kvm_x86_flush_tlb_all)(vcpu);
+
+	/* Flushing all ASIDs flushes the current ASID... */
+	kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 }
 
 static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
@@ -3415,6 +3426,12 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	}
 
 	static_call(kvm_x86_flush_tlb_guest)(vcpu);
+
+	/*
+	 * Flushing all "guest" TLB is always a superset of Hyper-V's fine
+	 * grained flushing.
+	 */
+	kvm_hv_vcpu_purge_flush_tlb(vcpu);
 }
 
 
@@ -3566,20 +3583,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vcpu->arch.arch_capabilities = data;
 		break;
-	case MSR_IA32_PERF_CAPABILITIES: {
-		struct kvm_msr_entry msr_ent = {.index = msr, .data = 0};
-
+	case MSR_IA32_PERF_CAPABILITIES:
 		if (!msr_info->host_initiated)
 			return 1;
-		if (kvm_get_msr_feature(&msr_ent))
-			return 1;
-		if (data & ~msr_ent.data)
+		if (data & ~kvm_caps.supported_perf_cap)
 			return 1;
 
 		vcpu->arch.perf_capabilities = data;
 		kvm_pmu_refresh(vcpu);
 		return 0;
-	}
 	case MSR_EFER:
 		return set_efer(vcpu, msr_info);
 	case MSR_K7_HWCR:
@@ -3651,7 +3663,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	}
 	case MSR_IA32_SMBASE:
-		if (!msr_info->host_initiated)
+		if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated)
 			return 1;
 		vcpu->arch.smbase = data;
 		break;
@@ -4067,7 +4079,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vcpu->arch.ia32_misc_enable_msr;
 		break;
 	case MSR_IA32_SMBASE:
-		if (!msr_info->host_initiated)
+		if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated)
 			return 1;
 		msr_info->data = vcpu->arch.smbase;
 		break;
@@ -4425,7 +4437,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		    KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL |
 		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
 		if (sched_info_on())
-			r |= KVM_XEN_HVM_CONFIG_RUNSTATE;
+			r |= KVM_XEN_HVM_CONFIG_RUNSTATE |
+			     KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG;
 		break;
 #endif
 	case KVM_CAP_SYNC_REGS:
@@ -4441,6 +4454,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r |= KVM_X86_DISABLE_EXITS_MWAIT;
 		break;
 	case KVM_CAP_X86_SMM:
+		if (!IS_ENABLED(CONFIG_KVM_SMM))
+			break;
+
 		/* SMBASE is usually relocated above 1M on modern chipsets,
 		 * and SMM handlers might indeed rely on 4G segment limits,
 		 * so do not report SMM to be available if real mode is
@@ -4481,7 +4497,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0;
 		break;
 	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
-		r = kvm_x86_ops.enable_direct_tlbflush != NULL;
+		r = kvm_x86_ops.enable_l2_tlb_flush != NULL;
 		break;
 	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
 		r = kvm_x86_ops.nested_ops->enable_evmcs != NULL;
@@ -4897,13 +4913,6 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu)
-{
-	kvm_make_request(KVM_REQ_SMI, vcpu);
-
-	return 0;
-}
-
 static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
 					   struct kvm_tpr_access_ctl *tac)
 {
@@ -5039,8 +5048,10 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 
 	process_nmi(vcpu);
 
+#ifdef CONFIG_KVM_SMM
 	if (kvm_check_request(KVM_REQ_SMI, vcpu))
 		process_smi(vcpu);
+#endif
 
 	/*
 	 * KVM's ABI only allows for one exception to be migrated.  Luckily,
@@ -5068,16 +5079,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	    ex->pending && ex->has_payload)
 		kvm_deliver_exception_payload(vcpu, ex);
 
+	memset(events, 0, sizeof(*events));
+
 	/*
 	 * The API doesn't provide the instruction length for software
 	 * exceptions, so don't report them. As long as the guest RIP
 	 * isn't advanced, we should expect to encounter the exception
 	 * again.
 	 */
-	if (kvm_exception_is_soft(ex->vector)) {
-		events->exception.injected = 0;
-		events->exception.pending = 0;
-	} else {
+	if (!kvm_exception_is_soft(ex->vector)) {
 		events->exception.injected = ex->injected;
 		events->exception.pending = ex->pending;
 		/*
@@ -5097,20 +5107,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	events->interrupt.injected =
 		vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
 	events->interrupt.nr = vcpu->arch.interrupt.nr;
-	events->interrupt.soft = 0;
 	events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
 
 	events->nmi.injected = vcpu->arch.nmi_injected;
 	events->nmi.pending = vcpu->arch.nmi_pending != 0;
 	events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu);
-	events->nmi.pad = 0;
 
-	events->sipi_vector = 0; /* never valid when reporting to user space */
+	/* events->sipi_vector is never valid when reporting to user space */
 
+#ifdef CONFIG_KVM_SMM
 	events->smi.smm = is_smm(vcpu);
 	events->smi.pending = vcpu->arch.smi_pending;
 	events->smi.smm_inside_nmi =
 		!!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK);
+#endif
 	events->smi.latched_init = kvm_lapic_latched_init(vcpu);
 
 	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
@@ -5122,12 +5132,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 		events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 		events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT;
 	}
-
-	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
-static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm);
-
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
 {
@@ -5200,6 +5206,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+#ifdef CONFIG_KVM_SMM
 		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
 			kvm_leave_nested(vcpu);
 			kvm_smm_changed(vcpu, events->smi.smm);
@@ -5214,6 +5221,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
 		}
 
+#else
+		if (events->smi.smm || events->smi.pending ||
+		    events->smi.smm_inside_nmi)
+			return -EINVAL;
+#endif
+
 		if (lapic_in_kernel(vcpu)) {
 			if (events->smi.latched_init)
 				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
@@ -5497,10 +5510,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		}
 		return r;
 	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
-		if (!kvm_x86_ops.enable_direct_tlbflush)
+		if (!kvm_x86_ops.enable_l2_tlb_flush)
 			return -ENOTTY;
 
-		return static_call(kvm_x86_enable_direct_tlbflush)(vcpu);
+		return static_call(kvm_x86_enable_l2_tlb_flush)(vcpu);
 
 	case KVM_CAP_HYPERV_ENFORCE_CPUID:
 		return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]);
@@ -5580,7 +5593,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_SMI: {
-		r = kvm_vcpu_ioctl_smi(vcpu);
+		r = kvm_inject_smi(vcpu);
 		break;
 	}
 	case KVM_SET_CPUID: {
@@ -6239,9 +6252,7 @@ split_irqchip_unlock:
 		break;
 	case KVM_CAP_X86_USER_SPACE_MSR:
 		r = -EINVAL;
-		if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL |
-				     KVM_MSR_EXIT_REASON_UNKNOWN |
-				     KVM_MSR_EXIT_REASON_FILTER))
+		if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK)
 			break;
 		kvm->arch.user_space_msr_mask = cap->args[0];
 		r = 0;
@@ -6418,7 +6429,7 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
 	if (!user_range->nmsrs)
 		return 0;
 
-	if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE))
+	if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK)
 		return -EINVAL;
 
 	if (!user_range->flags)
@@ -6452,7 +6463,7 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm,
 	int r = 0;
 	u32 i;
 
-	if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
+	if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK)
 		return -EINVAL;
 
 	for (i = 0; i < ARRAY_SIZE(filter->ranges); i++)
@@ -7125,8 +7136,8 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
 	return handled;
 }
 
-static void kvm_set_segment(struct kvm_vcpu *vcpu,
-			struct kvm_segment *var, int seg)
+void kvm_set_segment(struct kvm_vcpu *vcpu,
+		     struct kvm_segment *var, int seg)
 {
 	static_call(kvm_x86_set_segment)(vcpu, var, seg);
 }
@@ -7162,16 +7173,6 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read);
 
- gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
-				struct x86_exception *exception)
-{
-	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
-
-	u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
-	access |= PFERR_FETCH_MASK;
-	return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
-}
-
 gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
 			       struct x86_exception *exception)
 {
@@ -7284,15 +7285,6 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
 }
 
-static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
-		unsigned long addr, void *val, unsigned int bytes)
-{
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes);
-
-	return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE;
-}
-
 static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
 				      struct kvm_vcpu *vcpu, u64 access,
 				      struct x86_exception *exception)
@@ -8084,26 +8076,6 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
 }
 
-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);
-}
-
-static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
-{
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
-	return vcpu->arch.smbase;
-}
-
-static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
-{
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
-	vcpu->arch.smbase = smbase;
-}
-
 static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
 			      u32 pmc)
 {
@@ -8178,18 +8150,13 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
 	return emul_to_vcpu(ctxt)->arch.hflags;
 }
 
-static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt)
+#ifndef CONFIG_KVM_SMM
+static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
 {
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
-	kvm_smm_changed(vcpu, false);
-}
-
-static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt,
-				  const char *smstate)
-{
-	return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate);
+	WARN_ON_ONCE(1);
+	return X86EMUL_UNHANDLEABLE;
 }
+#endif
 
 static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt)
 {
@@ -8215,7 +8182,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.write_gpr           = emulator_write_gpr,
 	.read_std            = emulator_read_std,
 	.write_std           = emulator_write_std,
-	.read_phys           = kvm_read_guest_phys_system,
 	.fetch               = kvm_fetch_guest_virt,
 	.read_emulated       = emulator_read_emulated,
 	.write_emulated      = emulator_write_emulated,
@@ -8235,11 +8201,8 @@ static const struct x86_emulate_ops emulate_ops = {
 	.cpl                 = emulator_get_cpl,
 	.get_dr              = emulator_get_dr,
 	.set_dr              = emulator_set_dr,
-	.get_smbase          = emulator_get_smbase,
-	.set_smbase          = emulator_set_smbase,
 	.set_msr_with_filter = emulator_set_msr_with_filter,
 	.get_msr_with_filter = emulator_get_msr_with_filter,
-	.set_msr             = emulator_set_msr,
 	.get_msr             = emulator_get_msr,
 	.check_pmc	     = emulator_check_pmc,
 	.read_pmc            = emulator_read_pmc,
@@ -8254,7 +8217,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.guest_has_rdpid     = emulator_guest_has_rdpid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
 	.get_hflags          = emulator_get_hflags,
-	.exiting_smm         = emulator_exiting_smm,
 	.leave_smm           = emulator_leave_smm,
 	.triple_fault        = emulator_triple_fault,
 	.set_xcr             = emulator_set_xcr,
@@ -8327,8 +8289,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 		     cs_db				? X86EMUL_MODE_PROT32 :
 							  X86EMUL_MODE_PROT16;
 	BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
-	BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
-	BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
 
 	ctxt->interruptibility = 0;
 	ctxt->have_exception = false;
@@ -8587,29 +8547,6 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
 static int complete_emulated_pio(struct kvm_vcpu *vcpu);
 
-static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
-{
-	trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm);
-
-	if (entering_smm) {
-		vcpu->arch.hflags |= HF_SMM_MASK;
-	} else {
-		vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK);
-
-		/* Process a latched INIT or SMI, if any.  */
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
-
-		/*
-		 * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
-		 * on SMM exit we still need to reload them from
-		 * guest memory
-		 */
-		vcpu->arch.pdptrs_from_userspace = false;
-	}
-
-	kvm_mmu_reset_context(vcpu);
-}
-
 static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 				unsigned long *db)
 {
@@ -8841,7 +8778,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 						  write_fault_to_spt,
 						  emulation_type))
 				return 1;
-			if (ctxt->have_exception) {
+
+			if (ctxt->have_exception &&
+			    !(emulation_type & EMULTYPE_SKIP)) {
 				/*
 				 * #UD should result in just EMULATION_FAILED, and trap-like
 				 * exception should not be encountered during decode.
@@ -9105,9 +9044,11 @@ static void tsc_khz_changed(void *data)
 	struct cpufreq_freqs *freq = data;
 	unsigned long khz = 0;
 
+	WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_CONSTANT_TSC));
+
 	if (data)
 		khz = freq->new;
-	else if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+	else
 		khz = cpufreq_quick_get(raw_smp_processor_id());
 	if (!khz)
 		khz = tsc_khz;
@@ -9128,8 +9069,10 @@ static void kvm_hyperv_tsc_notifier(void)
 	hyperv_stop_tsc_emulation();
 
 	/* TSC frequency always matches when on Hyper-V */
-	for_each_present_cpu(cpu)
-		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+		for_each_present_cpu(cpu)
+			per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	}
 	kvm_caps.max_guest_tsc_khz = tsc_khz;
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
@@ -9266,10 +9209,10 @@ static void kvm_timer_init(void)
 		}
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
-	}
 
-	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
-			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
+		cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
+				  kvmclock_cpu_online, kvmclock_cpu_down_prep);
+	}
 }
 
 #ifdef CONFIG_X86_64
@@ -9429,10 +9372,11 @@ void kvm_arch_exit(void)
 #endif
 	kvm_lapic_exit();
 
-	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
 					    CPUFREQ_TRANSITION_NOTIFIER);
-	cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
+		cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
+	}
 #ifdef CONFIG_X86_64
 	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
 	irq_work_sync(&pvclock_irq_work);
@@ -9999,6 +9943,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
 	 * in order to make progress and get back here for another iteration.
 	 * The kvm_x86_ops hooks communicate this by returning -EBUSY.
 	 */
+#ifdef CONFIG_KVM_SMM
 	if (vcpu->arch.smi_pending) {
 		r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY;
 		if (r < 0)
@@ -10011,6 +9956,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
 		} else
 			static_call(kvm_x86_enable_smi_window)(vcpu);
 	}
+#endif
 
 	if (vcpu->arch.nmi_pending) {
 		r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY;
@@ -10086,246 +10032,6 @@ static void process_nmi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
-static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
-{
-	u32 flags = 0;
-	flags |= seg->g       << 23;
-	flags |= seg->db      << 22;
-	flags |= seg->l       << 21;
-	flags |= seg->avl     << 20;
-	flags |= seg->present << 15;
-	flags |= seg->dpl     << 13;
-	flags |= seg->s       << 12;
-	flags |= seg->type    << 8;
-	return flags;
-}
-
-static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
-{
-	struct kvm_segment seg;
-	int offset;
-
-	kvm_get_segment(vcpu, &seg, n);
-	put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector);
-
-	if (n < 3)
-		offset = 0x7f84 + n * 12;
-	else
-		offset = 0x7f2c + (n - 3) * 12;
-
-	put_smstate(u32, buf, offset + 8, seg.base);
-	put_smstate(u32, buf, offset + 4, seg.limit);
-	put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
-}
-
-#ifdef CONFIG_X86_64
-static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
-{
-	struct kvm_segment seg;
-	int offset;
-	u16 flags;
-
-	kvm_get_segment(vcpu, &seg, n);
-	offset = 0x7e00 + n * 16;
-
-	flags = enter_smm_get_segment_flags(&seg) >> 8;
-	put_smstate(u16, buf, offset, seg.selector);
-	put_smstate(u16, buf, offset + 2, flags);
-	put_smstate(u32, buf, offset + 4, seg.limit);
-	put_smstate(u64, buf, offset + 8, seg.base);
-}
-#endif
-
-static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
-{
-	struct desc_ptr dt;
-	struct kvm_segment seg;
-	unsigned long val;
-	int i;
-
-	put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu));
-	put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu));
-	put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu));
-	put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu));
-
-	for (i = 0; i < 8; i++)
-		put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i));
-
-	kvm_get_dr(vcpu, 6, &val);
-	put_smstate(u32, buf, 0x7fcc, (u32)val);
-	kvm_get_dr(vcpu, 7, &val);
-	put_smstate(u32, buf, 0x7fc8, (u32)val);
-
-	kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
-	put_smstate(u32, buf, 0x7fc4, seg.selector);
-	put_smstate(u32, buf, 0x7f64, seg.base);
-	put_smstate(u32, buf, 0x7f60, seg.limit);
-	put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
-
-	kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
-	put_smstate(u32, buf, 0x7fc0, seg.selector);
-	put_smstate(u32, buf, 0x7f80, seg.base);
-	put_smstate(u32, buf, 0x7f7c, seg.limit);
-	put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
-
-	static_call(kvm_x86_get_gdt)(vcpu, &dt);
-	put_smstate(u32, buf, 0x7f74, dt.address);
-	put_smstate(u32, buf, 0x7f70, dt.size);
-
-	static_call(kvm_x86_get_idt)(vcpu, &dt);
-	put_smstate(u32, buf, 0x7f58, dt.address);
-	put_smstate(u32, buf, 0x7f54, dt.size);
-
-	for (i = 0; i < 6; i++)
-		enter_smm_save_seg_32(vcpu, buf, i);
-
-	put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
-
-	/* revision id */
-	put_smstate(u32, buf, 0x7efc, 0x00020000);
-	put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
-}
-
-#ifdef CONFIG_X86_64
-static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
-{
-	struct desc_ptr dt;
-	struct kvm_segment seg;
-	unsigned long val;
-	int i;
-
-	for (i = 0; i < 16; i++)
-		put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i));
-
-	put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu));
-	put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu));
-
-	kvm_get_dr(vcpu, 6, &val);
-	put_smstate(u64, buf, 0x7f68, val);
-	kvm_get_dr(vcpu, 7, &val);
-	put_smstate(u64, buf, 0x7f60, val);
-
-	put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu));
-	put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu));
-	put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu));
-
-	put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase);
-
-	/* revision id */
-	put_smstate(u32, buf, 0x7efc, 0x00020064);
-
-	put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer);
-
-	kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
-	put_smstate(u16, buf, 0x7e90, seg.selector);
-	put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
-	put_smstate(u32, buf, 0x7e94, seg.limit);
-	put_smstate(u64, buf, 0x7e98, seg.base);
-
-	static_call(kvm_x86_get_idt)(vcpu, &dt);
-	put_smstate(u32, buf, 0x7e84, dt.size);
-	put_smstate(u64, buf, 0x7e88, dt.address);
-
-	kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
-	put_smstate(u16, buf, 0x7e70, seg.selector);
-	put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
-	put_smstate(u32, buf, 0x7e74, seg.limit);
-	put_smstate(u64, buf, 0x7e78, seg.base);
-
-	static_call(kvm_x86_get_gdt)(vcpu, &dt);
-	put_smstate(u32, buf, 0x7e64, dt.size);
-	put_smstate(u64, buf, 0x7e68, dt.address);
-
-	for (i = 0; i < 6; i++)
-		enter_smm_save_seg_64(vcpu, buf, i);
-}
-#endif
-
-static void enter_smm(struct kvm_vcpu *vcpu)
-{
-	struct kvm_segment cs, ds;
-	struct desc_ptr dt;
-	unsigned long cr0;
-	char buf[512];
-
-	memset(buf, 0, 512);
-#ifdef CONFIG_X86_64
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
-		enter_smm_save_state_64(vcpu, buf);
-	else
-#endif
-		enter_smm_save_state_32(vcpu, buf);
-
-	/*
-	 * Give enter_smm() a chance to make ISA-specific changes to the vCPU
-	 * state (e.g. leave guest mode) after we've saved the state into the
-	 * SMM state-save area.
-	 */
-	static_call(kvm_x86_enter_smm)(vcpu, buf);
-
-	kvm_smm_changed(vcpu, true);
-	kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
-
-	if (static_call(kvm_x86_get_nmi_mask)(vcpu))
-		vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
-	else
-		static_call(kvm_x86_set_nmi_mask)(vcpu, true);
-
-	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
-	kvm_rip_write(vcpu, 0x8000);
-
-	cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
-	static_call(kvm_x86_set_cr0)(vcpu, cr0);
-	vcpu->arch.cr0 = cr0;
-
-	static_call(kvm_x86_set_cr4)(vcpu, 0);
-
-	/* Undocumented: IDT limit is set to zero on entry to SMM.  */
-	dt.address = dt.size = 0;
-	static_call(kvm_x86_set_idt)(vcpu, &dt);
-
-	kvm_set_dr(vcpu, 7, DR7_FIXED_1);
-
-	cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
-	cs.base = vcpu->arch.smbase;
-
-	ds.selector = 0;
-	ds.base = 0;
-
-	cs.limit    = ds.limit = 0xffffffff;
-	cs.type     = ds.type = 0x3;
-	cs.dpl      = ds.dpl = 0;
-	cs.db       = ds.db = 0;
-	cs.s        = ds.s = 1;
-	cs.l        = ds.l = 0;
-	cs.g        = ds.g = 1;
-	cs.avl      = ds.avl = 0;
-	cs.present  = ds.present = 1;
-	cs.unusable = ds.unusable = 0;
-	cs.padding  = ds.padding = 0;
-
-	kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
-	kvm_set_segment(vcpu, &ds, VCPU_SREG_DS);
-	kvm_set_segment(vcpu, &ds, VCPU_SREG_ES);
-	kvm_set_segment(vcpu, &ds, VCPU_SREG_FS);
-	kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
-	kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
-
-#ifdef CONFIG_X86_64
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
-		static_call(kvm_x86_set_efer)(vcpu, 0);
-#endif
-
-	kvm_update_cpuid_runtime(vcpu);
-	kvm_mmu_reset_context(vcpu);
-}
-
-static void process_smi(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.smi_pending = true;
-	kvm_make_request(KVM_REQ_EVENT, vcpu);
-}
-
 void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
 				       unsigned long *vcpu_bitmap)
 {
@@ -10516,20 +10222,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	bool req_immediate_exit = false;
 
-	/* Forbid vmenter if vcpu dirty ring is soft-full */
-	if (unlikely(vcpu->kvm->dirty_ring_size &&
-		     kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) {
-		vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
-		trace_kvm_dirty_ring_exit(vcpu);
-		r = 0;
-		goto out;
-	}
-
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) {
 			r = -EIO;
 			goto out;
 		}
+
+		if (kvm_dirty_ring_check_request(vcpu)) {
+			r = 0;
+			goto out;
+		}
+
 		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;
@@ -10553,14 +10256,27 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_mmu_sync_roots(vcpu);
 		if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu))
 			kvm_mmu_load_pgd(vcpu);
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
+
+		/*
+		 * Note, the order matters here, as flushing "all" TLB entries
+		 * also flushes the "current" TLB entries, i.e. servicing the
+		 * flush "all" will clear any request to flush "current".
+		 */
+		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
 			kvm_vcpu_flush_tlb_all(vcpu);
 
-			/* Flushing all ASIDs flushes the current ASID... */
-			kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
-		}
 		kvm_service_local_tlb_flush_requests(vcpu);
 
+		/*
+		 * Fall back to a "full" guest flush if Hyper-V's precise
+		 * flushing fails.  Note, Hyper-V's flushing is per-vCPU, but
+		 * the flushes are considered "remote" and not "local" because
+		 * the requests can be initiated from other vCPUs.
+		 */
+		if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) &&
+		    kvm_hv_vcpu_flush_tlb(vcpu))
+			kvm_vcpu_flush_tlb_guest(vcpu);
+
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
 			r = 0;
@@ -10585,8 +10301,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 		if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
 			record_steal_time(vcpu);
+#ifdef CONFIG_KVM_SMM
 		if (kvm_check_request(KVM_REQ_SMI, vcpu))
 			process_smi(vcpu);
+#endif
 		if (kvm_check_request(KVM_REQ_NMI, vcpu))
 			process_nmi(vcpu);
 		if (kvm_check_request(KVM_REQ_PMU, vcpu))
@@ -11834,7 +11552,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.regs_avail = ~0;
 	vcpu->arch.regs_dirty = ~0;
 
-	kvm_gpc_init(&vcpu->arch.pv_time);
+	kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm, vcpu, KVM_HOST_USES_PFN);
 
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -11900,6 +11618,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
 
 	kvm_async_pf_hash_reset(vcpu);
+
+	vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap;
 	kvm_pmu_init(vcpu);
 
 	vcpu->arch.pending_external_vector = -1;
@@ -12334,7 +12054,6 @@ bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id;
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp);
 
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 {
@@ -12909,10 +12628,12 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 	     static_call(kvm_x86_nmi_allowed)(vcpu, false)))
 		return true;
 
+#ifdef CONFIG_KVM_SMM
 	if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
 	    (vcpu->arch.smi_pending &&
 	     static_call(kvm_x86_smi_allowed)(vcpu, false)))
 		return true;
+#endif
 
 	if (kvm_arch_interrupt_allowed(vcpu) &&
 	    (kvm_cpu_has_interrupt(vcpu) ||
@@ -12953,7 +12674,9 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
 		return true;
 
 	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+#ifdef CONFIG_KVM_SMM
 		kvm_test_request(KVM_REQ_SMI, vcpu) ||
+#endif
 		 kvm_test_request(KVM_REQ_EVENT, vcpu))
 		return true;