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

Pull kvm updates from Paolo Bonzini:
 "s390:

   - More phys_to_virt conversions

   - Improvement of AP management for VSIE (nested virtualization)

  ARM64:

   - Numerous fixes for the pathological lock inversion issue that
     plagued KVM/arm64 since... forever.

   - New framework allowing SMCCC-compliant hypercalls to be forwarded
     to userspace, hopefully paving the way for some more features being
     moved to VMMs rather than be implemented in the kernel.

   - Large rework of the timer code to allow a VM-wide offset to be
     applied to both virtual and physical counters as well as a
     per-timer, per-vcpu offset that complements the global one. This
     last part allows the NV timer code to be implemented on top.

   - A small set of fixes to make sure that we don't change anything
     affecting the EL1&0 translation regime just after having having
     taken an exception to EL2 until we have executed a DSB. This
     ensures that speculative walks started in EL1&0 have completed.

   - The usual selftest fixes and improvements.

  x86:

   - Optimize CR0.WP toggling by avoiding an MMU reload when TDP is
     enabled, and by giving the guest control of CR0.WP when EPT is
     enabled on VMX (VMX-only because SVM doesn't support per-bit
     controls)

   - Add CR0/CR4 helpers to query single bits, and clean up related code
     where KVM was interpreting kvm_read_cr4_bits()'s "unsigned long"
     return as a bool

   - Move AMD_PSFD to cpufeatures.h and purge KVM's definition

   - Avoid unnecessary writes+flushes when the guest is only adding new
     PTEs

   - Overhaul .sync_page() and .invlpg() to utilize .sync_page()'s
     optimizations when emulating invalidations

   - Clean up the range-based flushing APIs

   - Revamp the TDP MMU's reaping of Accessed/Dirty bits to clear a
     single A/D bit using a LOCK AND instead of XCHG, and skip all of
     the "handle changed SPTE" overhead associated with writing the
     entire entry

   - Track the number of "tail" entries in a pte_list_desc to avoid
     having to walk (potentially) all descriptors during insertion and
     deletion, which gets quite expensive if the guest is spamming
     fork()

   - Disallow virtualizing legacy LBRs if architectural LBRs are
     available, the two are mutually exclusive in hardware

   - Disallow writes to immutable feature MSRs (notably
     PERF_CAPABILITIES) after KVM_RUN, similar to CPUID features

   - Overhaul the vmx_pmu_caps selftest to better validate
     PERF_CAPABILITIES

   - Apply PMU filters to emulated events and add test coverage to the
     pmu_event_filter selftest

   - AMD SVM:
       - Add support for virtual NMIs
       - Fixes for edge cases related to virtual interrupts

   - Intel AMX:
       - Don't advertise XTILE_CFG in KVM_GET_SUPPORTED_CPUID if
         XTILE_DATA is not being reported due to userspace not opting in
         via prctl()
       - Fix a bug in emulation of ENCLS in compatibility mode
       - Allow emulation of NOP and PAUSE for L2
       - AMX selftests improvements
       - Misc cleanups

  MIPS:

   - Constify MIPS's internal callbacks (a leftover from the hardware
     enabling rework that landed in 6.3)

  Generic:

   - Drop unnecessary casts from "void *" throughout kvm_main.c

   - Tweak the layout of "struct kvm_mmu_memory_cache" to shrink the
     struct size by 8 bytes on 64-bit kernels by utilizing a padding
     hole

  Documentation:

   - Fix goof introduced by the conversion to rST"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (211 commits)
  KVM: s390: pci: fix virtual-physical confusion on module unload/load
  KVM: s390: vsie: clarifications on setting the APCB
  KVM: s390: interrupt: fix virtual-physical confusion for next alert GISA
  KVM: arm64: Have kvm_psci_vcpu_on() use WRITE_ONCE() to update mp_state
  KVM: arm64: Acquire mp_state_lock in kvm_arch_vcpu_ioctl_vcpu_init()
  KVM: selftests: Test the PMU event "Instructions retired"
  KVM: selftests: Copy full counter values from guest in PMU event filter test
  KVM: selftests: Use error codes to signal errors in PMU event filter test
  KVM: selftests: Print detailed info in PMU event filter asserts
  KVM: selftests: Add helpers for PMC asserts in PMU event filter test
  KVM: selftests: Add a common helper for the PMU event filter guest code
  KVM: selftests: Fix spelling mistake "perrmited" -> "permitted"
  KVM: arm64: vhe: Drop extra isb() on guest exit
  KVM: arm64: vhe: Synchronise with page table walker on MMU update
  KVM: arm64: pkvm: Document the side effects of kvm_flush_dcache_to_poc()
  KVM: arm64: nvhe: Synchronise with page table walker on TLBI
  KVM: arm64: Handle 32bit CNTPCTSS traps
  KVM: arm64: nvhe: Synchronise with page table walker on vcpu run
  KVM: arm64: vgic: Don't acquire its_lock before config_lock
  KVM: selftests: Add test to verify KVM's supported XCR0
  ...

5 files changed, 252 insertions, 76 deletions

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 05d38944a6c0..96936ddf1b3c 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -139,13 +139,18 @@ void recalc_intercepts(struct vcpu_svm *svm)
 
 	if (g->int_ctl & V_INTR_MASKING_MASK) {
 		/*
-		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8
-		 * does not affect any interrupt we may want to inject;
-		 * therefore, writes to CR8 are irrelevant to L0, as are
-		 * interrupt window vmexits.
+		 * If L2 is active and V_INTR_MASKING is enabled in vmcb12,
+		 * disable intercept of CR8 writes as L2's CR8 does not affect
+		 * any interrupt KVM may want to inject.
+		 *
+		 * Similarly, disable intercept of virtual interrupts (used to
+		 * detect interrupt windows) if the saved RFLAGS.IF is '0', as
+		 * the effective RFLAGS.IF for L1 interrupts will never be set
+		 * while L2 is running (L2's RFLAGS.IF doesn't affect L1 IRQs).
 		 */
 		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
-		vmcb_clr_intercept(c, INTERCEPT_VINTR);
+		if (!(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF))
+			vmcb_clr_intercept(c, INTERCEPT_VINTR);
 	}
 
 	/*
@@ -276,6 +281,11 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
 	if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl)))
 		return false;
 
+	if (CC((control->int_ctl & V_NMI_ENABLE_MASK) &&
+	       !vmcb12_is_intercept(control, INTERCEPT_NMI))) {
+		return false;
+	}
+
 	return true;
 }
 
@@ -416,22 +426,24 @@ void nested_sync_control_from_vmcb02(struct vcpu_svm *svm)
 
 	/* Only a few fields of int_ctl are written by the processor.  */
 	mask = V_IRQ_MASK | V_TPR_MASK;
-	if (!(svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) &&
-	    svm_is_intercept(svm, INTERCEPT_VINTR)) {
-		/*
-		 * In order to request an interrupt window, L0 is usurping
-		 * svm->vmcb->control.int_ctl and possibly setting V_IRQ
-		 * even if it was clear in L1's VMCB.  Restoring it would be
-		 * wrong.  However, in this case V_IRQ will remain true until
-		 * interrupt_window_interception calls svm_clear_vintr and
-		 * restores int_ctl.  We can just leave it aside.
-		 */
+	/*
+	 * Don't sync vmcb02 V_IRQ back to vmcb12 if KVM (L0) is intercepting
+	 * virtual interrupts in order to request an interrupt window, as KVM
+	 * has usurped vmcb02's int_ctl.  If an interrupt window opens before
+	 * the next VM-Exit, svm_clear_vintr() will restore vmcb12's int_ctl.
+	 * If no window opens, V_IRQ will be correctly preserved in vmcb12's
+	 * int_ctl (because it was never recognized while L2 was running).
+	 */
+	if (svm_is_intercept(svm, INTERCEPT_VINTR) &&
+	    !test_bit(INTERCEPT_VINTR, (unsigned long *)svm->nested.ctl.intercepts))
 		mask &= ~V_IRQ_MASK;
-	}
 
 	if (nested_vgif_enabled(svm))
 		mask |= V_GIF_MASK;
 
+	if (nested_vnmi_enabled(svm))
+		mask |= V_NMI_BLOCKING_MASK | V_NMI_PENDING_MASK;
+
 	svm->nested.ctl.int_ctl        &= ~mask;
 	svm->nested.ctl.int_ctl        |= svm->vmcb->control.int_ctl & mask;
 }
@@ -651,6 +663,17 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	else
 		int_ctl_vmcb01_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK);
 
+	if (vnmi) {
+		if (vmcb01->control.int_ctl & V_NMI_PENDING_MASK) {
+			svm->vcpu.arch.nmi_pending++;
+			kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
+		}
+		if (nested_vnmi_enabled(svm))
+			int_ctl_vmcb12_bits |= (V_NMI_PENDING_MASK |
+						V_NMI_ENABLE_MASK |
+						V_NMI_BLOCKING_MASK);
+	}
+
 	/* Copied from vmcb01.  msrpm_base can be overwritten later.  */
 	vmcb02->control.nested_ctl = vmcb01->control.nested_ctl;
 	vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa;
@@ -1021,6 +1044,28 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 	svm_switch_vmcb(svm, &svm->vmcb01);
 
+	/*
+	 * Rules for synchronizing int_ctl bits from vmcb02 to vmcb01:
+	 *
+	 * V_IRQ, V_IRQ_VECTOR, V_INTR_PRIO_MASK, V_IGN_TPR:  If L1 doesn't
+	 * intercept interrupts, then KVM will use vmcb02's V_IRQ (and related
+	 * flags) to detect interrupt windows for L1 IRQs (even if L1 uses
+	 * virtual interrupt masking).  Raise KVM_REQ_EVENT to ensure that
+	 * KVM re-requests an interrupt window if necessary, which implicitly
+	 * copies this bits from vmcb02 to vmcb01.
+	 *
+	 * V_TPR: If L1 doesn't use virtual interrupt masking, then L1's vTPR
+	 * is stored in vmcb02, but its value doesn't need to be copied from/to
+	 * vmcb01 because it is copied from/to the virtual APIC's TPR register
+	 * on each VM entry/exit.
+	 *
+	 * V_GIF: If nested vGIF is not used, KVM uses vmcb02's V_GIF for L1's
+	 * V_GIF.  However, GIF is architecturally clear on each VM exit, thus
+	 * there is no need to copy V_GIF from vmcb02 to vmcb01.
+	 */
+	if (!nested_exit_on_intr(svm))
+		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
+
 	if (unlikely(svm->lbrv_enabled && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
 		svm_copy_lbrs(vmcb12, vmcb02);
 		svm_update_lbrv(vcpu);
@@ -1029,6 +1074,20 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 		svm_update_lbrv(vcpu);
 	}
 
+	if (vnmi) {
+		if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK)
+			vmcb01->control.int_ctl |= V_NMI_BLOCKING_MASK;
+		else
+			vmcb01->control.int_ctl &= ~V_NMI_BLOCKING_MASK;
+
+		if (vcpu->arch.nmi_pending) {
+			vcpu->arch.nmi_pending--;
+			vmcb01->control.int_ctl |= V_NMI_PENDING_MASK;
+		} else {
+			vmcb01->control.int_ctl &= ~V_NMI_PENDING_MASK;
+		}
+	}
+
 	/*
 	 * On vmexit the  GIF is set to false and
 	 * no event can be injected in L1.
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index cc77a0681800..5fa939e411d8 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -161,7 +161,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		data &= ~pmu->reserved_bits;
 		if (data != pmc->eventsel) {
 			pmc->eventsel = data;
-			kvm_pmu_request_counter_reprogam(pmc);
+			kvm_pmu_request_counter_reprogram(pmc);
 		}
 		return 0;
 	}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a1b08359769b..ca32389f3c36 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs {
 #endif
 	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
 	{ .index = MSR_IA32_PRED_CMD,			.always = false },
+	{ .index = MSR_IA32_FLUSH_CMD,			.always = false },
 	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
@@ -234,6 +235,8 @@ module_param(dump_invalid_vmcb, bool, 0644);
 bool intercept_smi = true;
 module_param(intercept_smi, bool, 0444);
 
+bool vnmi = true;
+module_param(vnmi, bool, 0444);
 
 static bool svm_gp_erratum_intercept = true;
 
@@ -1315,6 +1318,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 	if (kvm_vcpu_apicv_active(vcpu))
 		avic_init_vmcb(svm, vmcb);
 
+	if (vnmi)
+		svm->vmcb->control.int_ctl |= V_NMI_ENABLE_MASK;
+
 	if (vgif) {
 		svm_clr_intercept(svm, INTERCEPT_STGI);
 		svm_clr_intercept(svm, INTERCEPT_CLGI);
@@ -1588,6 +1594,16 @@ static void svm_set_vintr(struct vcpu_svm *svm)
 	svm_set_intercept(svm, INTERCEPT_VINTR);
 
 	/*
+	 * Recalculating intercepts may have cleared the VINTR intercept.  If
+	 * V_INTR_MASKING is enabled in vmcb12, then the effective RFLAGS.IF
+	 * for L1 physical interrupts is L1's RFLAGS.IF at the time of VMRUN.
+	 * Requesting an interrupt window if save.RFLAGS.IF=0 is pointless as
+	 * interrupts will never be unblocked while L2 is running.
+	 */
+	if (!svm_is_intercept(svm, INTERCEPT_VINTR))
+		return;
+
+	/*
 	 * This is just a dummy VINTR to actually cause a vmexit to happen.
 	 * Actual injection of virtual interrupts happens through EVENTINJ.
 	 */
@@ -2484,16 +2500,29 @@ static int task_switch_interception(struct kvm_vcpu *vcpu)
 			       has_error_code, error_code);
 }
 
+static void svm_clr_iret_intercept(struct vcpu_svm *svm)
+{
+	if (!sev_es_guest(svm->vcpu.kvm))
+		svm_clr_intercept(svm, INTERCEPT_IRET);
+}
+
+static void svm_set_iret_intercept(struct vcpu_svm *svm)
+{
+	if (!sev_es_guest(svm->vcpu.kvm))
+		svm_set_intercept(svm, INTERCEPT_IRET);
+}
+
 static int iret_interception(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	++vcpu->stat.nmi_window_exits;
 	svm->awaiting_iret_completion = true;
-	if (!sev_es_guest(vcpu->kvm)) {
-		svm_clr_intercept(svm, INTERCEPT_IRET);
+
+	svm_clr_iret_intercept(svm);
+	if (!sev_es_guest(vcpu->kvm))
 		svm->nmi_iret_rip = kvm_rip_read(vcpu);
-	}
+
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	return 1;
 }
@@ -2876,7 +2905,7 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
 static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	int r;
+	int ret = 0;
 
 	u32 ecx = msr->index;
 	u64 data = msr->data;
@@ -2946,21 +2975,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 */
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
 		break;
-	case MSR_IA32_PRED_CMD:
-		if (!msr->host_initiated &&
-		    !guest_has_pred_cmd_msr(vcpu))
-			return 1;
-
-		if (data & ~PRED_CMD_IBPB)
-			return 1;
-		if (!boot_cpu_has(X86_FEATURE_IBPB))
-			return 1;
-		if (!data)
-			break;
-
-		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
-		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
 		if (!msr->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
@@ -3013,10 +3027,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 * guest via direct_access_msrs, and switch it via user return.
 		 */
 		preempt_disable();
-		r = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull);
+		ret = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull);
 		preempt_enable();
-		if (r)
-			return 1;
+		if (ret)
+			break;
 
 		svm->tsc_aux = data;
 		break;
@@ -3074,7 +3088,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
-	return 0;
+	return ret;
 }
 
 static int msr_interception(struct kvm_vcpu *vcpu)
@@ -3485,11 +3499,43 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu)
 		return;
 
 	svm->nmi_masked = true;
-	if (!sev_es_guest(vcpu->kvm))
-		svm_set_intercept(svm, INTERCEPT_IRET);
+	svm_set_iret_intercept(svm);
 	++vcpu->stat.nmi_injections;
 }
 
+static bool svm_is_vnmi_pending(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!is_vnmi_enabled(svm))
+		return false;
+
+	return !!(svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK);
+}
+
+static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!is_vnmi_enabled(svm))
+		return false;
+
+	if (svm->vmcb->control.int_ctl & V_NMI_PENDING_MASK)
+		return false;
+
+	svm->vmcb->control.int_ctl |= V_NMI_PENDING_MASK;
+	vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
+
+	/*
+	 * Because the pending NMI is serviced by hardware, KVM can't know when
+	 * the NMI is "injected", but for all intents and purposes, passing the
+	 * NMI off to hardware counts as injection.
+	 */
+	++vcpu->stat.nmi_injections;
+
+	return true;
+}
+
 static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3585,6 +3631,35 @@ static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
 }
 
+static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (is_vnmi_enabled(svm))
+		return svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK;
+	else
+		return svm->nmi_masked;
+}
+
+static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (is_vnmi_enabled(svm)) {
+		if (masked)
+			svm->vmcb->control.int_ctl |= V_NMI_BLOCKING_MASK;
+		else
+			svm->vmcb->control.int_ctl &= ~V_NMI_BLOCKING_MASK;
+
+	} else {
+		svm->nmi_masked = masked;
+		if (masked)
+			svm_set_iret_intercept(svm);
+		else
+			svm_clr_iret_intercept(svm);
+	}
+}
+
 bool svm_nmi_blocked(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3596,8 +3671,10 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu)
 	if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm))
 		return false;
 
-	return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) ||
-	       svm->nmi_masked;
+	if (svm_get_nmi_mask(vcpu))
+		return true;
+
+	return vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK;
 }
 
 static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
@@ -3615,26 +3692,6 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 	return 1;
 }
 
-static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
-{
-	return to_svm(vcpu)->nmi_masked;
-}
-
-static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	if (masked) {
-		svm->nmi_masked = true;
-		if (!sev_es_guest(vcpu->kvm))
-			svm_set_intercept(svm, INTERCEPT_IRET);
-	} else {
-		svm->nmi_masked = false;
-		if (!sev_es_guest(vcpu->kvm))
-			svm_clr_intercept(svm, INTERCEPT_IRET);
-	}
-}
-
 bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3715,7 +3772,16 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm->nmi_masked && !svm->awaiting_iret_completion)
+	/*
+	 * KVM should never request an NMI window when vNMI is enabled, as KVM
+	 * allows at most one to-be-injected NMI and one pending NMI, i.e. if
+	 * two NMIs arrive simultaneously, KVM will inject one and set
+	 * V_NMI_PENDING for the other.  WARN, but continue with the standard
+	 * single-step approach to try and salvage the pending NMI.
+	 */
+	WARN_ON_ONCE(is_vnmi_enabled(svm));
+
+	if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion)
 		return; /* IRET will cause a vm exit */
 
 	if (!gif_set(svm)) {
@@ -3777,13 +3843,13 @@ static void svm_flush_tlb_all(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * When running on Hyper-V with EnlightenedNptTlb enabled, remote TLB
-	 * flushes should be routed to hv_remote_flush_tlb() without requesting
+	 * flushes should be routed to hv_flush_remote_tlbs() without requesting
 	 * a "regular" remote flush.  Reaching this point means either there's
-	 * a KVM bug or a prior hv_remote_flush_tlb() call failed, both of
+	 * a KVM bug or a prior hv_flush_remote_tlbs() call failed, both of
 	 * which might be fatal to the guest.  Yell, but try to recover.
 	 */
 	if (WARN_ON_ONCE(svm_hv_is_enlightened_tlb_enabled(vcpu)))
-		hv_remote_flush_tlb(vcpu->kvm);
+		hv_flush_remote_tlbs(vcpu->kvm);
 
 	svm_flush_tlb_asid(vcpu);
 }
@@ -4142,7 +4208,7 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
 {
 	switch (index) {
 	case MSR_IA32_MCG_EXT_CTL:
-	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
+	case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR:
 		return false;
 	case MSR_IA32_SMBASE:
 		if (!IS_ENABLED(CONFIG_KVM_SMM))
@@ -4184,8 +4250,18 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF);
 
+	svm->vnmi_enabled = vnmi && guest_cpuid_has(vcpu, X86_FEATURE_VNMI);
+
 	svm_recalc_instruction_intercepts(vcpu, svm);
 
+	if (boot_cpu_has(X86_FEATURE_IBPB))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0,
+				     !!guest_has_pred_cmd_msr(vcpu));
+
+	if (boot_cpu_has(X86_FEATURE_FLUSH_L1D))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
+				     !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D));
+
 	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
 	if (sev_guest(vcpu->kvm)) {
 		best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
@@ -4563,7 +4639,6 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 					void *insn, int insn_len)
 {
 	bool smep, smap, is_user;
-	unsigned long cr4;
 	u64 error_code;
 
 	/* Emulation is always possible when KVM has access to all guest state. */
@@ -4655,9 +4730,8 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK))
 		goto resume_guest;
 
-	cr4 = kvm_read_cr4(vcpu);
-	smep = cr4 & X86_CR4_SMEP;
-	smap = cr4 & X86_CR4_SMAP;
+	smep = kvm_is_cr4_bit_set(vcpu, X86_CR4_SMEP);
+	smap = kvm_is_cr4_bit_set(vcpu, X86_CR4_SMAP);
 	is_user = svm_get_cpl(vcpu) == 3;
 	if (smap && (!smep || is_user)) {
 		pr_err_ratelimited("SEV Guest triggered AMD Erratum 1096\n");
@@ -4795,6 +4869,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.patch_hypercall = svm_patch_hypercall,
 	.inject_irq = svm_inject_irq,
 	.inject_nmi = svm_inject_nmi,
+	.is_vnmi_pending = svm_is_vnmi_pending,
+	.set_vnmi_pending = svm_set_vnmi_pending,
 	.inject_exception = svm_inject_exception,
 	.cancel_injection = svm_cancel_injection,
 	.interrupt_allowed = svm_interrupt_allowed,
@@ -4937,6 +5013,9 @@ static __init void svm_set_cpu_caps(void)
 		if (vgif)
 			kvm_cpu_cap_set(X86_FEATURE_VGIF);
 
+		if (vnmi)
+			kvm_cpu_cap_set(X86_FEATURE_VNMI);
+
 		/* Nested VM can receive #VMEXIT instead of triggering #GP */
 		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
 	}
@@ -5088,6 +5167,16 @@ static __init int svm_hardware_setup(void)
 			pr_info("Virtual GIF supported\n");
 	}
 
+	vnmi = vgif && vnmi && boot_cpu_has(X86_FEATURE_VNMI);
+	if (vnmi)
+		pr_info("Virtual NMI enabled\n");
+
+	if (!vnmi) {
+		svm_x86_ops.is_vnmi_pending = NULL;
+		svm_x86_ops.set_vnmi_pending = NULL;
+	}
+
+
 	if (lbrv) {
 		if (!boot_cpu_has(X86_FEATURE_LBRV))
 			lbrv = false;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 839809972da1..f44751dd8d5d 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -36,6 +36,7 @@ extern bool npt_enabled;
 extern int vgif;
 extern bool intercept_smi;
 extern bool x2avic_enabled;
+extern bool vnmi;
 
 /*
  * Clean bits in VMCB.
@@ -265,6 +266,7 @@ struct vcpu_svm {
 	bool pause_filter_enabled         : 1;
 	bool pause_threshold_enabled      : 1;
 	bool vgif_enabled                 : 1;
+	bool vnmi_enabled                 : 1;
 
 	u32 ldr_reg;
 	u32 dfr_reg;
@@ -539,6 +541,12 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm)
 	return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE;
 }
 
+static inline bool nested_vnmi_enabled(struct vcpu_svm *svm)
+{
+	return svm->vnmi_enabled &&
+	       (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK);
+}
+
 static inline bool is_x2apic_msrpm_offset(u32 offset)
 {
 	/* 4 msrs per u8, and 4 u8 in u32 */
@@ -548,6 +556,27 @@ static inline bool is_x2apic_msrpm_offset(u32 offset)
 	       (msr < (APIC_BASE_MSR + 0x100));
 }
 
+static inline struct vmcb *get_vnmi_vmcb_l1(struct vcpu_svm *svm)
+{
+	if (!vnmi)
+		return NULL;
+
+	if (is_guest_mode(&svm->vcpu))
+		return NULL;
+	else
+		return svm->vmcb01.ptr;
+}
+
+static inline bool is_vnmi_enabled(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = get_vnmi_vmcb_l1(svm);
+
+	if (vmcb)
+		return !!(vmcb->control.int_ctl & V_NMI_ENABLE_MASK);
+	else
+		return false;
+}
+
 /* svm.c */
 #define MSR_INVALID				0xffffffffU
 
diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h
index 786d46d73a8e..f85bc617ffe4 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.h
+++ b/arch/x86/kvm/svm/svm_onhyperv.h
@@ -45,9 +45,8 @@ static inline __init void svm_hv_hardware_setup(void)
 	if (npt_enabled &&
 	    ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) {
 		pr_info(KBUILD_MODNAME ": Hyper-V enlightened NPT TLB flush enabled\n");
-		svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb;
-		svm_x86_ops.tlb_remote_flush_with_range =
-				hv_remote_flush_tlb_with_range;
+		svm_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs;
+		svm_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range;
 	}
 
 	if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) {