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

Pull more kvm updates from Paolo Bonzini:
  Generic:

   - Clean up locking of all vCPUs for a VM by using the *_nest_lock()
     family of functions, and move duplicated code to virt/kvm/. kernel/
     patches acked by Peter Zijlstra

   - Add MGLRU support to the access tracking perf test

  ARM fixes:

   - Make the irqbypass hooks resilient to changes in the GSI<->MSI
     routing, avoiding behind stale vLPI mappings being left behind. The
     fix is to resolve the VGIC IRQ using the host IRQ (which is stable)
     and nuking the vLPI mapping upon a routing change

   - Close another VGIC race where vCPU creation races with VGIC
     creation, leading to in-flight vCPUs entering the kernel w/o
     private IRQs allocated

   - Fix a build issue triggered by the recently added workaround for
     Ampere's AC04_CPU_23 erratum

   - Correctly sign-extend the VA when emulating a TLBI instruction
     potentially targeting a VNCR mapping

   - Avoid dereferencing a NULL pointer in the VGIC debug code, which
     can happen if the device doesn't have any mapping yet

  s390:

   - Fix interaction between some filesystems and Secure Execution

   - Some cleanups and refactorings, preparing for an upcoming big
     series

  x86:

   - Wait for target vCPU to ack KVM_REQ_UPDATE_PROTECTED_GUEST_STATE
     to fix a race between AP destroy and VMRUN

   - Decrypt and dump the VMSA in dump_vmcb() if debugging enabled for
     the VM

   - Refine and harden handling of spurious faults

   - Add support for ALLOWED_SEV_FEATURES

   - Add #VMGEXIT to the set of handlers special cased for
     CONFIG_RETPOLINE=y

   - Treat DEBUGCTL[5:2] as reserved to pave the way for virtualizing
     features that utilize those bits

   - Don't account temporary allocations in sev_send_update_data()

   - Add support for KVM_CAP_X86_BUS_LOCK_EXIT on SVM, via Bus Lock
     Threshold

   - Unify virtualization of IBRS on nested VM-Exit, and cross-vCPU
     IBPB, between SVM and VMX

   - Advertise support to userspace for WRMSRNS and PREFETCHI

   - Rescan I/O APIC routes after handling EOI that needed to be
     intercepted due to the old/previous routing, but not the
     new/current routing

   - Add a module param to control and enumerate support for device
     posted interrupts

   - Fix a potential overflow with nested virt on Intel systems running
     32-bit kernels

   - Flush shadow VMCSes on emergency reboot

   - Add support for SNP to the various SEV selftests

   - Add a selftest to verify fastops instructions via forced emulation

   - Refine and optimize KVM's software processing of the posted
     interrupt bitmap, and share the harvesting code between KVM and the
     kernel's Posted MSI handler"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
  rtmutex_api: provide correct extern functions
  KVM: arm64: vgic-debug: Avoid dereferencing NULL ITE pointer
  KVM: arm64: vgic-init: Plug vCPU vs. VGIC creation race
  KVM: arm64: Unmap vLPIs affected by changes to GSI routing information
  KVM: arm64: Resolve vLPI by host IRQ in vgic_v4_unset_forwarding()
  KVM: arm64: Protect vLPI translation with vgic_irq::irq_lock
  KVM: arm64: Use lock guard in vgic_v4_set_forwarding()
  KVM: arm64: Mask out non-VA bits from TLBI VA* on VNCR invalidation
  arm64: sysreg: Drag linux/kconfig.h to work around vdso build issue
  KVM: s390: Simplify and move pv code
  KVM: s390: Refactor and split some gmap helpers
  KVM: s390: Remove unneeded srcu lock
  s390: Remove unneeded includes
  s390/uv: Improve splitting of large folios that cannot be split while dirty
  s390/uv: Always return 0 from s390_wiggle_split_folio() if successful
  s390/uv: Don't return 0 from make_hva_secure() if the operation was not successful
  rust: add helper for mutex_trylock
  RISC-V: KVM: use kvm_trylock_all_vcpus when locking all vCPUs
  KVM: arm64: use kvm_trylock_all_vcpus when locking all vCPUs
  x86: KVM: SVM: use kvm_lock_all_vcpus instead of a custom implementation
  ...

23 files changed, 567 insertions, 379 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6569b453546b..b2d006756e02 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -978,6 +978,7 @@ void kvm_set_cpu_caps(void)
 		F(FZRM),
 		F(FSRS),
 		F(FSRC),
+		F(WRMSRNS),
 		F(AMX_FP16),
 		F(AVX_IFMA),
 		F(LAM),
@@ -1093,6 +1094,7 @@ void kvm_set_cpu_caps(void)
 		F(AMD_SSB_NO),
 		F(AMD_STIBP),
 		F(AMD_STIBP_ALWAYS_ON),
+		F(AMD_IBRS_SAME_MODE),
 		F(AMD_PSFD),
 		F(AMD_IBPB_RET),
 	);
@@ -1150,6 +1152,7 @@ void kvm_set_cpu_caps(void)
 
 	kvm_cpu_cap_init(CPUID_8000_0021_EAX,
 		F(NO_NESTED_DATA_BP),
+		F(WRMSR_XX_BASE_NS),
 		/*
 		 * Synthesize "LFENCE is serializing" into the AMD-defined entry
 		 * in KVM's supported CPUID, i.e. if the feature is reported as
@@ -1163,10 +1166,13 @@ void kvm_set_cpu_caps(void)
 		SYNTHESIZED_F(LFENCE_RDTSC),
 		/* SmmPgCfgLock */
 		F(NULL_SEL_CLR_BASE),
+		/* UpperAddressIgnore */
 		F(AUTOIBRS),
+		F(PREFETCHI),
 		EMULATED_F(NO_SMM_CTL_MSR),
 		/* PrefetchCtlMsr */
-		F(WRMSR_XX_BASE_NS),
+		/* GpOnUserCpuid */
+		/* EPSF */
 		SYNTHESIZED_F(SBPB),
 		SYNTHESIZED_F(IBPB_BRTYPE),
 		SYNTHESIZED_F(SRSO_NO),
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 995eb5054360..45dae2d5d2f1 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -296,11 +296,8 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
 		    index == RTC_GSI) {
 			u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode);
 
-			if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
-						e->fields.dest_id, dm) ||
-			    kvm_apic_pending_eoi(vcpu, e->fields.vector))
-				__set_bit(e->fields.vector,
-					  ioapic_handled_vectors);
+			kvm_scan_ioapic_irq(vcpu, e->fields.dest_id, dm,
+					    e->fields.vector, ioapic_handled_vectors);
 		}
 	}
 	spin_unlock(&ioapic->lock);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 539333ac4b38..aa8cb4ac0479 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -120,4 +120,6 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu,
 			   ulong *ioapic_handled_vectors);
 void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 			    ulong *ioapic_handled_vectors);
+void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode,
+			 u8 vector, unsigned long *ioapic_handled_vectors);
 #endif
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 8136695f7b96..d6d792b5d1bd 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -402,6 +402,33 @@ void kvm_arch_post_irq_routing_update(struct kvm *kvm)
 	kvm_make_scan_ioapic_request(kvm);
 }
 
+void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode,
+			 u8 vector, unsigned long *ioapic_handled_vectors)
+{
+	/*
+	 * Intercept EOI if the vCPU is the target of the new IRQ routing, or
+	 * the vCPU has a pending IRQ from the old routing, i.e. if the vCPU
+	 * may receive a level-triggered IRQ in the future, or already received
+	 * level-triggered IRQ.  The EOI needs to be intercepted and forwarded
+	 * to I/O APIC emulation so that the IRQ can be de-asserted.
+	 */
+	if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, dest_id, dest_mode)) {
+		__set_bit(vector, ioapic_handled_vectors);
+	} else if (kvm_apic_pending_eoi(vcpu, vector)) {
+		__set_bit(vector, ioapic_handled_vectors);
+
+		/*
+		 * Track the highest pending EOI for which the vCPU is NOT the
+		 * target in the new routing.  Only the EOI for the IRQ that is
+		 * in-flight (for the old routing) needs to be intercepted, any
+		 * future IRQs that arrive on this vCPU will be coincidental to
+		 * the level-triggered routing and don't need to be intercepted.
+		 */
+		if ((int)vector > vcpu->arch.highest_stale_pending_ioapic_eoi)
+			vcpu->arch.highest_stale_pending_ioapic_eoi = vector;
+	}
+}
+
 void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 			    ulong *ioapic_handled_vectors)
 {
@@ -424,11 +451,11 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
-			if (irq.trig_mode &&
-			    (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
-						 irq.dest_id, irq.dest_mode) ||
-			     kvm_apic_pending_eoi(vcpu, irq.vector)))
-				__set_bit(irq.vector, ioapic_handled_vectors);
+			if (!irq.trig_mode)
+				continue;
+
+			kvm_scan_ioapic_irq(vcpu, irq.dest_id, irq.dest_mode,
+					    irq.vector, ioapic_handled_vectors);
 		}
 	}
 	srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c9de81cc27e1..73418dc0ebb2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -655,27 +655,29 @@ static u8 count_vectors(void *bitmap)
 	return count;
 }
 
-bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
+bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr)
 {
+	unsigned long pir_vals[NR_PIR_WORDS];
+	u32 *__pir = (void *)pir_vals;
 	u32 i, vec;
-	u32 pir_val, irr_val, prev_irr_val;
+	u32 irr_val, prev_irr_val;
 	int max_updated_irr;
 
 	max_updated_irr = -1;
 	*max_irr = -1;
 
+	if (!pi_harvest_pir(pir, pir_vals))
+		return false;
+
 	for (i = vec = 0; i <= 7; i++, vec += 32) {
 		u32 *p_irr = (u32 *)(regs + APIC_IRR + i * 0x10);
 
-		irr_val = *p_irr;
-		pir_val = READ_ONCE(pir[i]);
-
-		if (pir_val) {
-			pir_val = xchg(&pir[i], 0);
+		irr_val = READ_ONCE(*p_irr);
 
+		if (__pir[i]) {
 			prev_irr_val = irr_val;
 			do {
-				irr_val = prev_irr_val | pir_val;
+				irr_val = prev_irr_val | __pir[i];
 			} while (prev_irr_val != irr_val &&
 				 !try_cmpxchg(p_irr, &prev_irr_val, irr_val));
 
@@ -691,7 +693,7 @@ bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
 }
 EXPORT_SYMBOL_GPL(__kvm_apic_update_irr);
 
-bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr)
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	bool irr_updated = __kvm_apic_update_irr(pir, apic->regs, max_irr);
@@ -1459,6 +1461,14 @@ static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 	if (!kvm_ioapic_handles_vector(apic, vector))
 		return;
 
+	/*
+	 * If the intercepted EOI is for an IRQ that was pending from previous
+	 * routing, then re-scan the I/O APIC routes as EOIs for the IRQ likely
+	 * no longer need to be intercepted.
+	 */
+	if (apic->vcpu->arch.highest_stale_pending_ioapic_eoi == vector)
+		kvm_make_request(KVM_REQ_SCAN_IOAPIC, apic->vcpu);
+
 	/* Request a KVM exit to inform the userspace IOAPIC. */
 	if (irqchip_split(apic->vcpu->kvm)) {
 		apic->vcpu->arch.pending_ioapic_eoi = vector;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index e33c969439f7..4ce30db65828 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -103,8 +103,8 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 			   int shorthand, unsigned int dest, int dest_mode);
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
 void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec);
-bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr);
-bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr);
+bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr);
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr);
 void kvm_apic_update_ppr(struct kvm_vcpu *vcpu);
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
 		     struct dest_map *dest_map);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7b3f1783ab3c..cbc84c6abc2e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3020,7 +3020,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	}
 
 	if (is_shadow_present_pte(*sptep)) {
-		if (prefetch)
+		if (prefetch && is_last_spte(*sptep, level) &&
+		    pfn == spte_to_pfn(*sptep))
 			return RET_PF_SPURIOUS;
 
 		/*
@@ -3034,7 +3035,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 			child = spte_to_child_sp(pte);
 			drop_parent_pte(vcpu->kvm, child, sptep);
 			flush = true;
-		} else if (pfn != spte_to_pfn(*sptep)) {
+		} else if (WARN_ON_ONCE(pfn != spte_to_pfn(*sptep))) {
 			drop_spte(vcpu->kvm, sptep);
 			flush = true;
 		} else
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 405874f4d088..7f3d7229b2c1 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -378,7 +378,7 @@ static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte,
 	/* Zapping leaf spte is allowed only when write lock is held. */
 	lockdep_assert_held_write(&kvm->mmu_lock);
 	/* Because write lock is held, operation should success. */
-	ret = static_call(kvm_x86_remove_external_spte)(kvm, gfn, level, old_pfn);
+	ret = kvm_x86_call(remove_external_spte)(kvm, gfn, level, old_pfn);
 	KVM_BUG_ON(ret, kvm);
 }
 
@@ -485,8 +485,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
 	}
 
 	if (is_mirror_sp(sp) &&
-	    WARN_ON(static_call(kvm_x86_free_external_spt)(kvm, base_gfn, sp->role.level,
-							  sp->external_spt))) {
+	    WARN_ON(kvm_x86_call(free_external_spt)(kvm, base_gfn, sp->role.level,
+						    sp->external_spt))) {
 		/*
 		 * Failed to free page table page in mirror page table and
 		 * there is nothing to do further.
@@ -538,12 +538,12 @@ static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sp
 	 * external page table, or leaf.
 	 */
 	if (is_leaf) {
-		ret = static_call(kvm_x86_set_external_spte)(kvm, gfn, level, new_pfn);
+		ret = kvm_x86_call(set_external_spte)(kvm, gfn, level, new_pfn);
 	} else {
 		void *external_spt = get_external_spt(gfn, new_spte, level);
 
 		KVM_BUG_ON(!external_spt, kvm);
-		ret = static_call(kvm_x86_link_external_spt)(kvm, gfn, level, external_spt);
+		ret = kvm_x86_call(link_external_spt)(kvm, gfn, level, external_spt);
 	}
 	if (ret)
 		__kvm_tdp_mmu_write_spte(sptep, old_spte);
@@ -1153,13 +1153,12 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
 	if (WARN_ON_ONCE(sp->role.level != fault->goal_level))
 		return RET_PF_RETRY;
 
-	if (fault->prefetch && is_shadow_present_pte(iter->old_spte))
-		return RET_PF_SPURIOUS;
-
 	if (is_shadow_present_pte(iter->old_spte) &&
-	    is_access_allowed(fault, iter->old_spte) &&
-	    is_last_spte(iter->old_spte, iter->level))
+	    (fault->prefetch || is_access_allowed(fault, iter->old_spte)) &&
+	    is_last_spte(iter->old_spte, iter->level)) {
+		WARN_ON_ONCE(fault->pfn != spte_to_pfn(iter->old_spte));
 		return RET_PF_SPURIOUS;
+	}
 
 	if (unlikely(!fault->slot))
 		new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 834b67672d50..8427a48b8b7a 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -678,6 +678,33 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa;
 	vmcb02->control.msrpm_base_pa = vmcb01->control.msrpm_base_pa;
 
+	/*
+	 * Stash vmcb02's counter if the guest hasn't moved past the guilty
+	 * instruction; otherwise, reset the counter to '0'.
+	 *
+	 * In order to detect if L2 has made forward progress or not, track the
+	 * RIP at which a bus lock has occurred on a per-vmcb12 basis.  If RIP
+	 * is changed, guest has clearly made forward progress, bus_lock_counter
+	 * still remained '1', so reset bus_lock_counter to '0'. Eg. In the
+	 * scenario, where a buslock happened in L1 before VMRUN, the bus lock
+	 * firmly happened on an instruction in the past. Even if vmcb01's
+	 * counter is still '1', (because the guilty instruction got patched),
+	 * the vCPU has clearly made forward progress and so KVM should reset
+	 * vmcb02's counter to '0'.
+	 *
+	 * If the RIP hasn't changed, stash the bus lock counter at nested VMRUN
+	 * to prevent the same guilty instruction from triggering a VM-Exit. Eg.
+	 * if userspace rate-limits the vCPU, then it's entirely possible that
+	 * L1's tick interrupt is pending by the time userspace re-runs the
+	 * vCPU.  If KVM unconditionally clears the counter on VMRUN, then when
+	 * L1 re-enters L2, the same instruction will trigger a VM-Exit and the
+	 * entire cycle start over.
+	 */
+	if (vmcb02->save.rip && (svm->nested.ctl.bus_lock_rip == vmcb02->save.rip))
+		vmcb02->control.bus_lock_counter = 1;
+	else
+		vmcb02->control.bus_lock_counter = 0;
+
 	/* Done at vmrun: asid.  */
 
 	/* Also overwritten later if necessary.  */
@@ -1039,8 +1066,17 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 	}
 
+	/*
+	 * Invalidate bus_lock_rip unless KVM is still waiting for the guest
+	 * to make forward progress before re-enabling bus lock detection.
+	 */
+	if (!vmcb02->control.bus_lock_counter)
+		svm->nested.ctl.bus_lock_rip = INVALID_GPA;
+
 	nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr);
 
+	kvm_nested_vmexit_handle_ibrs(vcpu);
+
 	svm_switch_vmcb(svm, &svm->vmcb01);
 
 	/*
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 1aa0f07d3a63..5a69b657dae9 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -561,6 +561,8 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
 		return -EFAULT;
 
+	sev->policy = params.policy;
+
 	memset(&start, 0, sizeof(start));
 
 	dh_blob = NULL;
@@ -1593,11 +1595,11 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* allocate memory for header and transport buffer */
 	ret = -ENOMEM;
-	hdr = kzalloc(params.hdr_len, GFP_KERNEL_ACCOUNT);
+	hdr = kzalloc(params.hdr_len, GFP_KERNEL);
 	if (!hdr)
 		goto e_unpin;
 
-	trans_data = kzalloc(params.trans_len, GFP_KERNEL_ACCOUNT);
+	trans_data = kzalloc(params.trans_len, GFP_KERNEL);
 	if (!trans_data)
 		goto e_free_hdr;
 
@@ -1883,70 +1885,6 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 	atomic_set_release(&src_sev->migration_in_progress, 0);
 }
 
-/* vCPU mutex subclasses.  */
-enum sev_migration_role {
-	SEV_MIGRATION_SOURCE = 0,
-	SEV_MIGRATION_TARGET,
-	SEV_NR_MIGRATION_ROLES,
-};
-
-static int sev_lock_vcpus_for_migration(struct kvm *kvm,
-					enum sev_migration_role role)
-{
-	struct kvm_vcpu *vcpu;
-	unsigned long i, j;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (mutex_lock_killable_nested(&vcpu->mutex, role))
-			goto out_unlock;
-
-#ifdef CONFIG_PROVE_LOCKING
-		if (!i)
-			/*
-			 * Reset the role to one that avoids colliding with
-			 * the role used for the first vcpu mutex.
-			 */
-			role = SEV_NR_MIGRATION_ROLES;
-		else
-			mutex_release(&vcpu->mutex.dep_map, _THIS_IP_);
-#endif
-	}
-
-	return 0;
-
-out_unlock:
-
-	kvm_for_each_vcpu(j, vcpu, kvm) {
-		if (i == j)
-			break;
-
-#ifdef CONFIG_PROVE_LOCKING
-		if (j)
-			mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_);
-#endif
-
-		mutex_unlock(&vcpu->mutex);
-	}
-	return -EINTR;
-}
-
-static void sev_unlock_vcpus_for_migration(struct kvm *kvm)
-{
-	struct kvm_vcpu *vcpu;
-	unsigned long i;
-	bool first = true;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (first)
-			first = false;
-		else
-			mutex_acquire(&vcpu->mutex.dep_map,
-				      SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_);
-
-		mutex_unlock(&vcpu->mutex);
-	}
-}
-
 static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
 	struct kvm_sev_info *dst = to_kvm_sev_info(dst_kvm);
@@ -2084,10 +2022,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 		charged = true;
 	}
 
-	ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE);
+	ret = kvm_lock_all_vcpus(kvm);
 	if (ret)
 		goto out_dst_cgroup;
-	ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET);
+	ret = kvm_lock_all_vcpus(source_kvm);
 	if (ret)
 		goto out_dst_vcpu;
 
@@ -2101,9 +2039,9 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	ret = 0;
 
 out_source_vcpu:
-	sev_unlock_vcpus_for_migration(source_kvm);
+	kvm_unlock_all_vcpus(source_kvm);
 out_dst_vcpu:
-	sev_unlock_vcpus_for_migration(kvm);
+	kvm_unlock_all_vcpus(kvm);
 out_dst_cgroup:
 	/* Operates on the source on success, on the destination on failure.  */
 	if (charged)
@@ -2200,6 +2138,8 @@ static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET)
 		return -EINVAL;
 
+	sev->policy = params.policy;
+
 	sev->snp_context = snp_context_create(kvm, argp);
 	if (!sev->snp_context)
 		return -ENOTTY;
@@ -4007,10 +3947,8 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
 	 * Unless Creation is deferred until INIT, signal the vCPU to update
 	 * its state.
 	 */
-	if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT) {
-		kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
-		kvm_vcpu_kick(target_vcpu);
-	}
+	if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT)
+		kvm_make_request_and_kick(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
 
 	return 0;
 }
@@ -4468,6 +4406,7 @@ void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
 
 static void sev_es_init_vmcb(struct vcpu_svm *svm)
 {
+	struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
 	struct vmcb *vmcb = svm->vmcb01.ptr;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
@@ -4483,6 +4422,10 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
 		svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
 
+	if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
+		svm->vmcb->control.allowed_sev_features = sev->vmsa_features |
+							  VMCB_ALLOWED_SEV_FEATURES_VALID;
+
 	/* Can't intercept CR register access, HV can't modify CR registers */
 	svm_clr_intercept(svm, INTERCEPT_CR0_READ);
 	svm_clr_intercept(svm, INTERCEPT_CR4_READ);
@@ -4943,3 +4886,97 @@ int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
 
 	return level;
 }
+
+struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb_save_area *vmsa;
+	struct kvm_sev_info *sev;
+	int error = 0;
+	int ret;
+
+	if (!sev_es_guest(vcpu->kvm))
+		return NULL;
+
+	/*
+	 * If the VMSA has not yet been encrypted, return a pointer to the
+	 * current un-encrypted VMSA.
+	 */
+	if (!vcpu->arch.guest_state_protected)
+		return (struct vmcb_save_area *)svm->sev_es.vmsa;
+
+	sev = to_kvm_sev_info(vcpu->kvm);
+
+	/* Check if the SEV policy allows debugging */
+	if (sev_snp_guest(vcpu->kvm)) {
+		if (!(sev->policy & SNP_POLICY_DEBUG))
+			return NULL;
+	} else {
+		if (sev->policy & SEV_POLICY_NODBG)
+			return NULL;
+	}
+
+	if (sev_snp_guest(vcpu->kvm)) {
+		struct sev_data_snp_dbg dbg = {0};
+
+		vmsa = snp_alloc_firmware_page(__GFP_ZERO);
+		if (!vmsa)
+			return NULL;
+
+		dbg.gctx_paddr = __psp_pa(sev->snp_context);
+		dbg.src_addr = svm->vmcb->control.vmsa_pa;
+		dbg.dst_addr = __psp_pa(vmsa);
+
+		ret = sev_do_cmd(SEV_CMD_SNP_DBG_DECRYPT, &dbg, &error);
+
+		/*
+		 * Return the target page to a hypervisor page no matter what.
+		 * If this fails, the page can't be used, so leak it and don't
+		 * try to use it.
+		 */
+		if (snp_page_reclaim(vcpu->kvm, PHYS_PFN(__pa(vmsa))))
+			return NULL;
+
+		if (ret) {
+			pr_err("SEV: SNP_DBG_DECRYPT failed ret=%d, fw_error=%d (%#x)\n",
+			       ret, error, error);
+			free_page((unsigned long)vmsa);
+
+			return NULL;
+		}
+	} else {
+		struct sev_data_dbg dbg = {0};
+		struct page *vmsa_page;
+
+		vmsa_page = alloc_page(GFP_KERNEL);
+		if (!vmsa_page)
+			return NULL;
+
+		vmsa = page_address(vmsa_page);
+
+		dbg.handle = sev->handle;
+		dbg.src_addr = svm->vmcb->control.vmsa_pa;
+		dbg.dst_addr = __psp_pa(vmsa);
+		dbg.len = PAGE_SIZE;
+
+		ret = sev_do_cmd(SEV_CMD_DBG_DECRYPT, &dbg, &error);
+		if (ret) {
+			pr_err("SEV: SEV_CMD_DBG_DECRYPT failed ret=%d, fw_error=%d (0x%x)\n",
+			       ret, error, error);
+			__free_page(vmsa_page);
+
+			return NULL;
+		}
+	}
+
+	return vmsa;
+}
+
+void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa)
+{
+	/* If the VMSA has not yet been encrypted, nothing was allocated */
+	if (!vcpu->arch.guest_state_protected || !vmsa)
+		return;
+
+	free_page((unsigned long)vmsa);
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index ffb34dadff1c..ab9b947dbf4f 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -29,6 +29,7 @@
 #include <linux/cc_platform.h>
 #include <linux/smp.h>
 #include <linux/string_choices.h>
+#include <linux/mutex.h>
 
 #include <asm/apic.h>
 #include <asm/msr.h>
@@ -232,6 +233,8 @@ module_param(tsc_scaling, int, 0444);
 static bool avic;
 module_param(avic, bool, 0444);
 
+module_param(enable_device_posted_irqs, bool, 0444);
+
 bool __read_mostly dump_invalid_vmcb;
 module_param(dump_invalid_vmcb, bool, 0644);
 
@@ -250,6 +253,8 @@ static unsigned long iopm_base;
 
 DEFINE_PER_CPU(struct svm_cpu_data, svm_data);
 
+static DEFINE_MUTEX(vmcb_dump_mutex);
+
 /*
  * Only MSR_TSC_AUX is switched via the user return hook.  EFER is switched via
  * the VMCB, and the SYSCALL/SYSENTER MSRs are handled by VMLOAD/VMSAVE.
@@ -1369,6 +1374,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK;
 	}
 
+	if (vcpu->kvm->arch.bus_lock_detection_enabled)
+		svm_set_intercept(svm, INTERCEPT_BUSLOCK);
+
 	if (sev_guest(vcpu->kvm))
 		sev_init_vmcb(svm);
 
@@ -1478,25 +1486,10 @@ out:
 	return err;
 }
 
-static void svm_clear_current_vmcb(struct vmcb *vmcb)
-{
-	int i;
-
-	for_each_online_cpu(i)
-		cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL);
-}
-
 static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	/*
-	 * The vmcb page can be recycled, causing a false negative in
-	 * svm_vcpu_load(). So, ensure that no logical CPU has this
-	 * vmcb page recorded as its current vmcb.
-	 */
-	svm_clear_current_vmcb(svm->vmcb);
-
 	svm_leave_nested(vcpu);
 	svm_free_nested(svm);
 
@@ -1610,19 +1603,9 @@ static void svm_prepare_host_switch(struct kvm_vcpu *vcpu)
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
-	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
-
 	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
 		shrink_ple_window(vcpu);
 
-	if (sd->current_vmcb != svm->vmcb) {
-		sd->current_vmcb = svm->vmcb;
-
-		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT) &&
-		    static_branch_likely(&switch_vcpu_ibpb))
-			indirect_branch_prediction_barrier();
-	}
 	if (kvm_vcpu_apicv_active(vcpu))
 		avic_vcpu_load(vcpu, cpu);
 }
@@ -3221,17 +3204,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		}
 
 		/*
-		 * AMD changed the architectural behavior of bits 5:2.  On CPUs
-		 * without BusLockTrap, bits 5:2 control "external pins", but
-		 * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
-		 * and bits 5:3 are reserved-to-zero.  Sadly, old KVM allowed
-		 * the guest to set bits 5:2 despite not actually virtualizing
-		 * Performance-Monitoring/Breakpoint external pins.  Drop bits
-		 * 5:2 for backwards compatibility.
-		 */
-		data &= ~GENMASK(5, 2);
-
-		/*
 		 * Suppress BTF as KVM doesn't virtualize BTF, but there's no
 		 * way to communicate lack of support to the guest.
 		 */
@@ -3361,6 +3333,37 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
 	return kvm_handle_invpcid(vcpu, type, gva);
 }
 
+static inline int complete_userspace_buslock(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/*
+	 * If userspace has NOT changed RIP, then KVM's ABI is to let the guest
+	 * execute the bus-locking instruction.  Set the bus lock counter to '1'
+	 * to effectively step past the bus lock.
+	 */
+	if (kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))
+		svm->vmcb->control.bus_lock_counter = 1;
+
+	return 1;
+}
+
+static int bus_lock_exit(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
+	vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
+
+	vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
+	vcpu->arch.complete_userspace_io = complete_userspace_buslock;
+
+	if (is_guest_mode(vcpu))
+		svm->nested.ctl.bus_lock_rip = vcpu->arch.cui_linear_rip;
+
+	return 0;
+}
+
 static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[SVM_EXIT_READ_CR0]			= cr_interception,
 	[SVM_EXIT_READ_CR3]			= cr_interception,
@@ -3430,6 +3433,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[SVM_EXIT_INVPCID]                      = invpcid_interception,
 	[SVM_EXIT_IDLE_HLT]			= kvm_emulate_halt,
 	[SVM_EXIT_NPF]				= npf_interception,
+	[SVM_EXIT_BUS_LOCK]			= bus_lock_exit,
 	[SVM_EXIT_RSM]                          = rsm_interception,
 	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
 	[SVM_EXIT_AVIC_UNACCELERATED_ACCESS]	= avic_unaccelerated_access_interception,
@@ -3444,14 +3448,21 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct vmcb_save_area *save = &svm->vmcb->save;
 	struct vmcb_save_area *save01 = &svm->vmcb01.ptr->save;
+	char *vm_type;
 
 	if (!dump_invalid_vmcb) {
 		pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
 		return;
 	}
 
-	pr_err("VMCB %p, last attempted VMRUN on CPU %d\n",
-	       svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu);
+	guard(mutex)(&vmcb_dump_mutex);
+
+	vm_type = sev_snp_guest(vcpu->kvm) ? "SEV-SNP" :
+		  sev_es_guest(vcpu->kvm) ? "SEV-ES" :
+		  sev_guest(vcpu->kvm) ? "SEV" : "SVM";
+
+	pr_err("%s vCPU%u VMCB %p, last attempted VMRUN on CPU %d\n",
+	       vm_type, vcpu->vcpu_id, svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu);
 	pr_err("VMCB Control Area:\n");
 	pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff);
 	pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16);
@@ -3489,6 +3500,17 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id);
 	pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id);
 	pr_err("%-20s%016llx\n", "vmsa_pa:", control->vmsa_pa);
+	pr_err("%-20s%016llx\n", "allowed_sev_features:", control->allowed_sev_features);
+	pr_err("%-20s%016llx\n", "guest_sev_features:", control->guest_sev_features);
+
+	if (sev_es_guest(vcpu->kvm)) {
+		save = sev_decrypt_vmsa(vcpu);
+		if (!save)
+			goto no_vmsa;
+
+		save01 = save;
+	}
+
 	pr_err("VMCB State Save Area:\n");
 	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
 	       "es:",
@@ -3559,6 +3581,63 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	pr_err("%-15s %016llx %-13s %016llx\n",
 	       "excp_from:", save->last_excp_from,
 	       "excp_to:", save->last_excp_to);
+
+	if (sev_es_guest(vcpu->kvm)) {
+		struct sev_es_save_area *vmsa = (struct sev_es_save_area *)save;
+
+		pr_err("%-15s %016llx\n",
+		       "sev_features", vmsa->sev_features);
+
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "rax:", vmsa->rax, "rbx:", vmsa->rbx);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "rcx:", vmsa->rcx, "rdx:", vmsa->rdx);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "rsi:", vmsa->rsi, "rdi:", vmsa->rdi);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "rbp:", vmsa->rbp, "rsp:", vmsa->rsp);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "r8:", vmsa->r8, "r9:", vmsa->r9);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "r10:", vmsa->r10, "r11:", vmsa->r11);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "r12:", vmsa->r12, "r13:", vmsa->r13);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "r14:", vmsa->r14, "r15:", vmsa->r15);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "xcr0:", vmsa->xcr0, "xss:", vmsa->xss);
+	} else {
+		pr_err("%-15s %016llx %-13s %016lx\n",
+		       "rax:", save->rax, "rbx:",
+		       vcpu->arch.regs[VCPU_REGS_RBX]);
+		pr_err("%-15s %016lx %-13s %016lx\n",
+		       "rcx:", vcpu->arch.regs[VCPU_REGS_RCX],
+		       "rdx:", vcpu->arch.regs[VCPU_REGS_RDX]);
+		pr_err("%-15s %016lx %-13s %016lx\n",
+		       "rsi:", vcpu->arch.regs[VCPU_REGS_RSI],
+		       "rdi:", vcpu->arch.regs[VCPU_REGS_RDI]);
+		pr_err("%-15s %016lx %-13s %016llx\n",
+		       "rbp:", vcpu->arch.regs[VCPU_REGS_RBP],
+		       "rsp:", save->rsp);
+#ifdef CONFIG_X86_64
+		pr_err("%-15s %016lx %-13s %016lx\n",
+		       "r8:", vcpu->arch.regs[VCPU_REGS_R8],
+		       "r9:", vcpu->arch.regs[VCPU_REGS_R9]);
+		pr_err("%-15s %016lx %-13s %016lx\n",
+		       "r10:", vcpu->arch.regs[VCPU_REGS_R10],
+		       "r11:", vcpu->arch.regs[VCPU_REGS_R11]);
+		pr_err("%-15s %016lx %-13s %016lx\n",
+		       "r12:", vcpu->arch.regs[VCPU_REGS_R12],
+		       "r13:", vcpu->arch.regs[VCPU_REGS_R13]);
+		pr_err("%-15s %016lx %-13s %016lx\n",
+		       "r14:", vcpu->arch.regs[VCPU_REGS_R14],
+		       "r15:", vcpu->arch.regs[VCPU_REGS_R15]);
+#endif
+	}
+
+no_vmsa:
+	if (sev_es_guest(vcpu->kvm))
+		sev_free_decrypted_vmsa(vcpu, save);
 }
 
 static bool svm_check_exit_valid(u64 exit_code)
@@ -3595,6 +3674,10 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 		return kvm_emulate_halt(vcpu);
 	else if (exit_code == SVM_EXIT_NPF)
 		return npf_interception(vcpu);
+#ifdef CONFIG_KVM_AMD_SEV
+	else if (exit_code == SVM_EXIT_VMGEXIT)
+		return sev_handle_vmgexit(vcpu);
+#endif
 #endif
 	return svm_exit_handlers[exit_code](vcpu);
 }
@@ -5356,6 +5439,9 @@ static __init void svm_set_cpu_caps(void)
 		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
 	}
 
+	if (cpu_feature_enabled(X86_FEATURE_BUS_LOCK_THRESHOLD))
+		kvm_caps.has_bus_lock_exit = true;
+
 	/* CPUID 0x80000008 */
 	if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
 	    boot_cpu_has(X86_FEATURE_AMD_SSBD))
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f16b068c4228..e6f3c6a153a0 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -98,6 +98,7 @@ struct kvm_sev_info {
 	unsigned int asid;	/* ASID used for this guest */
 	unsigned int handle;	/* SEV firmware handle */
 	int fd;			/* SEV device fd */
+	unsigned long policy;
 	unsigned long pages_locked; /* Number of pages locked */
 	struct list_head regions_list;  /* List of registered regions */
 	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
@@ -114,6 +115,9 @@ struct kvm_sev_info {
 	struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */
 };
 
+#define SEV_POLICY_NODBG	BIT_ULL(0)
+#define SNP_POLICY_DEBUG	BIT_ULL(19)
+
 struct kvm_svm {
 	struct kvm kvm;
 
@@ -169,6 +173,7 @@ struct vmcb_ctrl_area_cached {
 	u64 nested_cr3;
 	u64 virt_ext;
 	u32 clean;
+	u64 bus_lock_rip;
 	union {
 #if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV)
 		struct hv_vmcb_enlightenments hv_enlightenments;
@@ -340,8 +345,6 @@ struct svm_cpu_data {
 	struct vmcb *save_area;
 	unsigned long save_area_pa;
 
-	struct vmcb *current_vmcb;
-
 	/* index = sev_asid, value = vmcb pointer */
 	struct vmcb **sev_vmcbs;
 };
@@ -785,6 +788,8 @@ void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
 int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
 int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
+struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu);
+void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa);
 #else
 static inline struct page *snp_safe_alloc_page_node(int node, gfp_t gfp)
 {
@@ -816,6 +821,11 @@ static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
 	return 0;
 }
 
+static inline struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu)
+{
+	return NULL;
+}
+static inline void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa) {}
 #endif
 
 /* vmenter.S */
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
index 8f46a06e2c44..a0c5e8781c33 100644
--- a/arch/x86/kvm/vmx/common.h
+++ b/arch/x86/kvm/vmx/common.h
@@ -71,8 +71,8 @@ static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu)
 
 #else
 
-static inline bool is_td(struct kvm *kvm) { return false; }
-static inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; }
+static __always_inline bool is_td(struct kvm *kvm) { return false; }
+static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; }
 
 #endif
 
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 94d5d907d37b..d1e02e567b57 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -12,7 +12,6 @@
 
 #ifdef CONFIG_KVM_INTEL_TDX
 static_assert(offsetof(struct vcpu_vmx, vt) == offsetof(struct vcpu_tdx, vt));
-#endif
 
 static void vt_disable_virtualization_cpu(void)
 {
@@ -240,7 +239,7 @@ static int vt_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
 	if (is_td_vcpu(vcpu))
 		return tdx_complete_emulated_msr(vcpu, err);
 
-	return kvm_complete_insn_gp(vcpu, err);
+	return vmx_complete_emulated_msr(vcpu, err);
 }
 
 #ifdef CONFIG_KVM_SMM
@@ -315,14 +314,6 @@ static void vt_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	return vmx_set_virtual_apic_mode(vcpu);
 }
 
-static void vt_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi = vcpu_to_pi_desc(vcpu);
-
-	pi_clear_on(pi);
-	memset(pi->pir, 0, sizeof(pi->pir));
-}
-
 static void vt_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
 {
 	if (is_td_vcpu(vcpu))
@@ -888,6 +879,13 @@ static int vt_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
 	return 0;
 }
 
+#define vt_op(name) vt_##name
+#define vt_op_tdx_only(name) vt_##name
+#else /* CONFIG_KVM_INTEL_TDX */
+#define vt_op(name) vmx_##name
+#define vt_op_tdx_only(name) NULL
+#endif /* CONFIG_KVM_INTEL_TDX */
+
 #define VMX_REQUIRED_APICV_INHIBITS				\
 	(BIT(APICV_INHIBIT_REASON_DISABLED) |			\
 	 BIT(APICV_INHIBIT_REASON_ABSENT) |			\
@@ -905,113 +903,113 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.hardware_unsetup = vmx_hardware_unsetup,
 
 	.enable_virtualization_cpu = vmx_enable_virtualization_cpu,
-	.disable_virtualization_cpu = vt_disable_virtualization_cpu,
+	.disable_virtualization_cpu = vt_op(disable_virtualization_cpu),
 	.emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu,
 
-	.has_emulated_msr = vt_has_emulated_msr,
+	.has_emulated_msr = vt_op(has_emulated_msr),
 
 	.vm_size = sizeof(struct kvm_vmx),
 
-	.vm_init = vt_vm_init,
-	.vm_pre_destroy = vt_vm_pre_destroy,
-	.vm_destroy = vt_vm_destroy,
+	.vm_init = vt_op(vm_init),
+	.vm_destroy = vt_op(vm_destroy),
+	.vm_pre_destroy = vt_op_tdx_only(vm_pre_destroy),
 
-	.vcpu_precreate = vt_vcpu_precreate,
-	.vcpu_create = vt_vcpu_create,
-	.vcpu_free = vt_vcpu_free,
-	.vcpu_reset = vt_vcpu_reset,
+	.vcpu_precreate = vt_op(vcpu_precreate),
+	.vcpu_create = vt_op(vcpu_create),
+	.vcpu_free = vt_op(vcpu_free),
+	.vcpu_reset = vt_op(vcpu_reset),
 
-	.prepare_switch_to_guest = vt_prepare_switch_to_guest,
-	.vcpu_load = vt_vcpu_load,
-	.vcpu_put = vt_vcpu_put,
+	.prepare_switch_to_guest = vt_op(prepare_switch_to_guest),
+	.vcpu_load = vt_op(vcpu_load),
+	.vcpu_put = vt_op(vcpu_put),
 
-	.update_exception_bitmap = vt_update_exception_bitmap,
+	.update_exception_bitmap = vt_op(update_exception_bitmap),
 	.get_feature_msr = vmx_get_feature_msr,
-	.get_msr = vt_get_msr,
-	.set_msr = vt_set_msr,
-
-	.get_segment_base = vt_get_segment_base,
-	.get_segment = vt_get_segment,
-	.set_segment = vt_set_segment,
-	.get_cpl = vt_get_cpl,
-	.get_cpl_no_cache = vt_get_cpl_no_cache,
-	.get_cs_db_l_bits = vt_get_cs_db_l_bits,
-	.is_valid_cr0 = vt_is_valid_cr0,
-	.set_cr0 = vt_set_cr0,
-	.is_valid_cr4 = vt_is_valid_cr4,
-	.set_cr4 = vt_set_cr4,
-	.set_efer = vt_set_efer,
-	.get_idt = vt_get_idt,
-	.set_idt = vt_set_idt,
-	.get_gdt = vt_get_gdt,
-	.set_gdt = vt_set_gdt,
-	.set_dr6 = vt_set_dr6,
-	.set_dr7 = vt_set_dr7,
-	.sync_dirty_debug_regs = vt_sync_dirty_debug_regs,
-	.cache_reg = vt_cache_reg,
-	.get_rflags = vt_get_rflags,
-	.set_rflags = vt_set_rflags,
-	.get_if_flag = vt_get_if_flag,
-
-	.flush_tlb_all = vt_flush_tlb_all,
-	.flush_tlb_current = vt_flush_tlb_current,
-	.flush_tlb_gva = vt_flush_tlb_gva,
-	.flush_tlb_guest = vt_flush_tlb_guest,
-
-	.vcpu_pre_run = vt_vcpu_pre_run,
-	.vcpu_run = vt_vcpu_run,
-	.handle_exit = vt_handle_exit,
+	.get_msr = vt_op(get_msr),
+	.set_msr = vt_op(set_msr),
+
+	.get_segment_base = vt_op(get_segment_base),
+	.get_segment = vt_op(get_segment),
+	.set_segment = vt_op(set_segment),
+	.get_cpl = vt_op(get_cpl),
+	.get_cpl_no_cache = vt_op(get_cpl_no_cache),
+	.get_cs_db_l_bits = vt_op(get_cs_db_l_bits),
+	.is_valid_cr0 = vt_op(is_valid_cr0),
+	.set_cr0 = vt_op(set_cr0),
+	.is_valid_cr4 = vt_op(is_valid_cr4),
+	.set_cr4 = vt_op(set_cr4),
+	.set_efer = vt_op(set_efer),
+	.get_idt = vt_op(get_idt),
+	.set_idt = vt_op(set_idt),
+	.get_gdt = vt_op(get_gdt),
+	.set_gdt = vt_op(set_gdt),
+	.set_dr6 = vt_op(set_dr6),
+	.set_dr7 = vt_op(set_dr7),
+	.sync_dirty_debug_regs = vt_op(sync_dirty_debug_regs),
+	.cache_reg = vt_op(cache_reg),
+	.get_rflags = vt_op(get_rflags),
+	.set_rflags = vt_op(set_rflags),
+	.get_if_flag = vt_op(get_if_flag),
+
+	.flush_tlb_all = vt_op(flush_tlb_all),
+	.flush_tlb_current = vt_op(flush_tlb_current),
+	.flush_tlb_gva = vt_op(flush_tlb_gva),
+	.flush_tlb_guest = vt_op(flush_tlb_guest),
+
+	.vcpu_pre_run = vt_op(vcpu_pre_run),
+	.vcpu_run = vt_op(vcpu_run),
+	.handle_exit = vt_op(handle_exit),
 	.skip_emulated_instruction = vmx_skip_emulated_instruction,
 	.update_emulated_instruction = vmx_update_emulated_instruction,
-	.set_interrupt_shadow = vt_set_interrupt_shadow,
-	.get_interrupt_shadow = vt_get_interrupt_shadow,
-	.patch_hypercall = vt_patch_hypercall,
-	.inject_irq = vt_inject_irq,
-	.inject_nmi = vt_inject_nmi,
-	.inject_exception = vt_inject_exception,
-	.cancel_injection = vt_cancel_injection,
-	.interrupt_allowed = vt_interrupt_allowed,
-	.nmi_allowed = vt_nmi_allowed,
-	.get_nmi_mask = vt_get_nmi_mask,
-	.set_nmi_mask = vt_set_nmi_mask,
-	.enable_nmi_window = vt_enable_nmi_window,
-	.enable_irq_window = vt_enable_irq_window,
-	.update_cr8_intercept = vt_update_cr8_intercept,
+	.set_interrupt_shadow = vt_op(set_interrupt_shadow),
+	.get_interrupt_shadow = vt_op(get_interrupt_shadow),
+	.patch_hypercall = vt_op(patch_hypercall),
+	.inject_irq = vt_op(inject_irq),
+	.inject_nmi = vt_op(inject_nmi),
+	.inject_exception = vt_op(inject_exception),
+	.cancel_injection = vt_op(cancel_injection),
+	.interrupt_allowed = vt_op(interrupt_allowed),
+	.nmi_allowed = vt_op(nmi_allowed),
+	.get_nmi_mask = vt_op(get_nmi_mask),
+	.set_nmi_mask = vt_op(set_nmi_mask),
+	.enable_nmi_window = vt_op(enable_nmi_window),
+	.enable_irq_window = vt_op(enable_irq_window),
+	.update_cr8_intercept = vt_op(update_cr8_intercept),
 
 	.x2apic_icr_is_split = false,
-	.set_virtual_apic_mode = vt_set_virtual_apic_mode,
-	.set_apic_access_page_addr = vt_set_apic_access_page_addr,
-	.refresh_apicv_exec_ctrl = vt_refresh_apicv_exec_ctrl,
-	.load_eoi_exitmap = vt_load_eoi_exitmap,
-	.apicv_pre_state_restore = vt_apicv_pre_state_restore,
+	.set_virtual_apic_mode = vt_op(set_virtual_apic_mode),
+	.set_apic_access_page_addr = vt_op(set_apic_access_page_addr),
+	.refresh_apicv_exec_ctrl = vt_op(refresh_apicv_exec_ctrl),
+	.load_eoi_exitmap = vt_op(load_eoi_exitmap),
+	.apicv_pre_state_restore = pi_apicv_pre_state_restore,
 	.required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
-	.hwapic_isr_update = vt_hwapic_isr_update,
-	.sync_pir_to_irr = vt_sync_pir_to_irr,
-	.deliver_interrupt = vt_deliver_interrupt,
+	.hwapic_isr_update = vt_op(hwapic_isr_update),
+	.sync_pir_to_irr = vt_op(sync_pir_to_irr),
+	.deliver_interrupt = vt_op(deliver_interrupt),
 	.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
 
-	.set_tss_addr = vt_set_tss_addr,
-	.set_identity_map_addr = vt_set_identity_map_addr,
+	.set_tss_addr = vt_op(set_tss_addr),
+	.set_identity_map_addr = vt_op(set_identity_map_addr),
 	.get_mt_mask = vmx_get_mt_mask,
 
-	.get_exit_info = vt_get_exit_info,
-	.get_entry_info = vt_get_entry_info,
+	.get_exit_info = vt_op(get_exit_info),
+	.get_entry_info = vt_op(get_entry_info),
 
-	.vcpu_after_set_cpuid = vt_vcpu_after_set_cpuid,
+	.vcpu_after_set_cpuid = vt_op(vcpu_after_set_cpuid),
 
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
-	.get_l2_tsc_offset = vt_get_l2_tsc_offset,
-	.get_l2_tsc_multiplier = vt_get_l2_tsc_multiplier,
-	.write_tsc_offset = vt_write_tsc_offset,
-	.write_tsc_multiplier = vt_write_tsc_multiplier,
+	.get_l2_tsc_offset = vt_op(get_l2_tsc_offset),
+	.get_l2_tsc_multiplier = vt_op(get_l2_tsc_multiplier),
+	.write_tsc_offset = vt_op(write_tsc_offset),
+	.write_tsc_multiplier = vt_op(write_tsc_multiplier),
 
-	.load_mmu_pgd = vt_load_mmu_pgd,
+	.load_mmu_pgd = vt_op(load_mmu_pgd),
 
 	.check_intercept = vmx_check_intercept,
 	.handle_exit_irqoff = vmx_handle_exit_irqoff,
 
-	.update_cpu_dirty_logging = vt_update_cpu_dirty_logging,
+	.update_cpu_dirty_logging = vt_op(update_cpu_dirty_logging),
 
 	.nested_ops = &vmx_nested_ops,
 
@@ -1019,38 +1017,38 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.pi_start_assignment = vmx_pi_start_assignment,
 
 #ifdef CONFIG_X86_64
-	.set_hv_timer = vt_set_hv_timer,
-	.cancel_hv_timer = vt_cancel_hv_timer,
+	.set_hv_timer = vt_op(set_hv_timer),
+	.cancel_hv_timer = vt_op(cancel_hv_timer),
 #endif
 
-	.setup_mce = vt_setup_mce,
+	.setup_mce = vt_op(setup_mce),
 
 #ifdef CONFIG_KVM_SMM
-	.smi_allowed = vt_smi_allowed,
-	.enter_smm = vt_enter_smm,
-	.leave_smm = vt_leave_smm,
-	.enable_smi_window = vt_enable_smi_window,
+	.smi_allowed = vt_op(smi_allowed),
+	.enter_smm = vt_op(enter_smm),
+	.leave_smm = vt_op(leave_smm),
+	.enable_smi_window = vt_op(enable_smi_window),
 #endif
 
-	.check_emulate_instruction = vt_check_emulate_instruction,
-	.apic_init_signal_blocked = vt_apic_init_signal_blocked,
+	.check_emulate_instruction = vt_op(check_emulate_instruction),
+	.apic_init_signal_blocked = vt_op(apic_init_signal_blocked),
 	.migrate_timers = vmx_migrate_timers,
 
-	.msr_filter_changed = vt_msr_filter_changed,
-	.complete_emulated_msr = vt_complete_emulated_msr,
+	.msr_filter_changed = vt_op(msr_filter_changed),
+	.complete_emulated_msr = vt_op(complete_emulated_msr),
 
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
 
 	.get_untagged_addr = vmx_get_untagged_addr,
 
-	.mem_enc_ioctl = vt_mem_enc_ioctl,
-	.vcpu_mem_enc_ioctl = vt_vcpu_mem_enc_ioctl,
+	.mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl),
+	.vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl),
 
-	.private_max_mapping_level = vt_gmem_private_max_mapping_level
+	.private_max_mapping_level = vt_op_tdx_only(gmem_private_max_mapping_level)
 };
 
 struct kvm_x86_init_ops vt_init_ops __initdata = {
-	.hardware_setup = vt_hardware_setup,
+	.hardware_setup = vt_op(hardware_setup),
 	.handle_intel_pt_intr = NULL,
 
 	.runtime_ops = &vt_x86_ops,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 71701e2414a4..7211c71d4241 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -302,7 +302,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 	cpu = get_cpu();
 	prev = vmx->loaded_vmcs;
 	vmx->loaded_vmcs = vmcs;
-	vmx_vcpu_load_vmcs(vcpu, cpu, prev);
+	vmx_vcpu_load_vmcs(vcpu, cpu);
 	vmx_sync_vmcs_host_state(vmx, prev);
 	put_cpu();
 
@@ -825,12 +825,30 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
+				       vmx->nested.msrs.misc_high);
+
+	return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
+}
+
 static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
 				       u32 count, u64 addr)
 {
 	if (count == 0)
 		return 0;
 
+	/*
+	 * Exceeding the limit results in architecturally _undefined_ behavior,
+	 * i.e. KVM is allowed to do literally anything in response to a bad
+	 * limit.  Immediately generate a consistency check so that code that
+	 * consumes the count doesn't need to worry about extreme edge cases.
+	 */
+	if (count > nested_vmx_max_atomic_switch_msrs(vcpu))
+		return -EINVAL;
+
 	if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) ||
 	    !kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1)))
 		return -EINVAL;
@@ -941,15 +959,6 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
-				       vmx->nested.msrs.misc_high);
-
-	return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
-}
-
 /*
  * Load guest's/host's msr at nested entry/exit.
  * return 0 for success, entry index for failure.
@@ -966,7 +975,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
 
 	for (i = 0; i < count; i++) {
-		if (unlikely(i >= max_msr_list_size))
+		if (WARN_ON_ONCE(i >= max_msr_list_size))
 			goto fail;
 
 		if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
@@ -1054,7 +1063,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
 
 	for (i = 0; i < count; i++) {
-		if (unlikely(i >= max_msr_list_size))
+		if (WARN_ON_ONCE(i >= max_msr_list_size))
 			return -EINVAL;
 
 		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
@@ -4521,12 +4530,12 @@ static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
 
 	cpu = get_cpu();
 	vmx->loaded_vmcs = &vmx->nested.vmcs02;
-	vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01);
+	vmx_vcpu_load_vmcs(vcpu, cpu);
 
 	sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
-	vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02);
+	vmx_vcpu_load_vmcs(vcpu, cpu);
 	put_cpu();
 }
 
@@ -5021,16 +5030,7 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
-	/*
-	 * If IBRS is advertised to the vCPU, KVM must flush the indirect
-	 * branch predictors when transitioning from L2 to L1, as L1 expects
-	 * hardware (KVM in this case) to provide separate predictor modes.
-	 * Bare metal isolates VMX root (host) from VMX non-root (guest), but
-	 * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
-	 * separate modes for L2 vs L1.
-	 */
-	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL))
-		indirect_branch_prediction_barrier();
+	kvm_nested_vmexit_handle_ibrs(vcpu);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 99d1d599ff8c..5c615e5845bf 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -34,7 +34,7 @@ static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
 
 #define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING
 
-struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
+static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
 {
 	return &(to_vt(vcpu)->pi_desc);
 }
@@ -148,9 +148,8 @@ after_clear_sn:
 
 static bool vmx_can_use_vtd_pi(struct kvm *kvm)
 {
-	return irqchip_in_kernel(kvm) && enable_apicv &&
-		kvm_arch_has_assigned_device(kvm) &&
-		irq_remapping_cap(IRQ_POSTING_CAP);
+	return irqchip_in_kernel(kvm) && kvm_arch_has_irq_bypass() &&
+	       kvm_arch_has_assigned_device(kvm);
 }
 
 /*
@@ -264,6 +263,14 @@ void __init pi_init_cpu(int cpu)
 	raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
 }
 
+void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi = vcpu_to_pi_desc(vcpu);
+
+	pi_clear_on(pi);
+	memset(pi->pir, 0, sizeof(pi->pir));
+}
+
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -281,7 +288,7 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
  */
 void vmx_pi_start_assignment(struct kvm *kvm)
 {
-	if (!irq_remapping_cap(IRQ_POSTING_CAP))
+	if (!kvm_arch_has_irq_bypass())
 		return;
 
 	kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK);
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 68605ca7ef68..80499ea0e674 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -5,12 +5,11 @@
 #include <linux/bitmap.h>
 #include <asm/posted_intr.h>
 
-struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu);
-
 void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
 void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu);
 void pi_wakeup_handler(void);
 void __init pi_init_cpu(int cpu);
+void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
 int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		       uint32_t guest_irq, bool set);
@@ -20,7 +19,7 @@ static inline int pi_find_highest_vector(struct pi_desc *pi_desc)
 {
 	int vec;
 
-	vec = find_last_bit((unsigned long *)pi_desc->pir, 256);
+	vec = find_last_bit(pi_desc->pir, 256);
 	return vec < 256 ? vec : -1;
 }
 
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index f6986dee6f8c..0a6cf5bff2aa 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -59,8 +59,7 @@
 	 * without the explicit restore, thinks the stack is getting walloped.
 	 * Using an unwind hint is problematic due to x86-64's dynamic alignment.
 	 */
-	mov %_ASM_BP, %_ASM_SP
-	pop %_ASM_BP
+	leave
 	RET
 .endm
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b12414108cbf..4953846cb30d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -117,6 +117,8 @@ module_param(enable_apicv, bool, 0444);
 bool __read_mostly enable_ipiv = true;
 module_param(enable_ipiv, bool, 0444);
 
+module_param(enable_device_posted_irqs, bool, 0444);
+
 /*
  * If nested=1, nested virtualization is supported, i.e., guests may use
  * VMX and be a hypervisor for its own guests. If nested=0, guests may not
@@ -772,8 +774,11 @@ void vmx_emergency_disable_virtualization_cpu(void)
 		return;
 
 	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
-			    loaded_vmcss_on_cpu_link)
+			    loaded_vmcss_on_cpu_link) {
 		vmcs_clear(v->vmcs);
+		if (v->shadow_vmcs)
+			vmcs_clear(v->shadow_vmcs);
+	}
 
 	kvm_cpu_vmxoff();
 }
@@ -1445,8 +1450,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 	}
 }
 
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
-			struct loaded_vmcs *buddy)
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
@@ -1473,17 +1477,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 	if (prev != vmx->loaded_vmcs->vmcs) {
 		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
 		vmcs_load(vmx->loaded_vmcs->vmcs);
-
-		/*
-		 * No indirect branch prediction barrier needed when switching
-		 * the active VMCS within a vCPU, unless IBRS is advertised to
-		 * the vCPU.  To minimize the number of IBPBs executed, KVM
-		 * performs IBPB on nested VM-Exit (a single nested transition
-		 * may switch the active VMCS multiple times).
-		 */
-		if (static_branch_likely(&switch_vcpu_ibpb) &&
-		    (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)))
-			indirect_branch_prediction_barrier();
 	}
 
 	if (!already_loaded) {
@@ -1522,7 +1515,7 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
 		shrink_ple_window(vcpu);
 
-	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
+	vmx_vcpu_load_vmcs(vcpu, cpu);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
 }
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 6d1e40ecc024..b5758c33c60f 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -354,8 +354,7 @@ static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu)
 	return vt->exit_intr_info;
 }
 
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
-			struct loaded_vmcs *buddy);
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu);
 int allocate_vpid(void);
 void free_vpid(int vpid);
 void vmx_set_constant_host_state(struct vcpu_vmx *vmx);
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 6bf8be570b2e..b4596f651232 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -57,6 +57,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
 int vmx_get_feature_msr(u32 msr, u64 *data);
 int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+#define vmx_complete_emulated_msr kvm_complete_insn_gp
 u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg);
 void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
@@ -163,71 +164,6 @@ void tdx_flush_tlb_current(struct kvm_vcpu *vcpu);
 void tdx_flush_tlb_all(struct kvm_vcpu *vcpu);
 void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
 int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
-#else
-static inline void tdx_disable_virtualization_cpu(void) {}
-static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; }
-static inline void tdx_mmu_release_hkid(struct kvm *kvm) {}
-static inline void tdx_vm_destroy(struct kvm *kvm) {}
-static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
-
-static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
-static inline void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) {}
-static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {}
-static inline void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) {}
-static inline int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
-static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
-{
-	return EXIT_FASTPATH_NONE;
-}
-static inline void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {}
-static inline void tdx_vcpu_put(struct kvm_vcpu *vcpu) {}
-static inline bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) { return false; }
-static inline int tdx_handle_exit(struct kvm_vcpu *vcpu,
-		enum exit_fastpath_completion fastpath) { return 0; }
-
-static inline void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
-					 int trig_mode, int vector) {}
-static inline void tdx_inject_nmi(struct kvm_vcpu *vcpu) {}
-static inline void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1,
-				     u64 *info2, u32 *intr_info, u32 *error_code) {}
-static inline bool tdx_has_emulated_msr(u32 index) { return false; }
-static inline int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
-static inline int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
-
-static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
-
-static inline int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
-					    enum pg_level level,
-					    void *private_spt)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
-					    enum pg_level level,
-					    void *private_spt)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
-					    enum pg_level level,
-					    kvm_pfn_t pfn)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
-					       enum pg_level level,
-					       kvm_pfn_t pfn)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void tdx_flush_tlb_current(struct kvm_vcpu *vcpu) {}
-static inline void tdx_flush_tlb_all(struct kvm_vcpu *vcpu) {}
-static inline void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) {}
-static inline int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) { return 0; }
 #endif
 
 #endif /* __KVM_X86_VMX_X86_OPS_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 570e7f8cbf64..b58a74c1722d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -226,6 +226,9 @@ EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
 bool __read_mostly enable_apicv = true;
 EXPORT_SYMBOL_GPL(enable_apicv);
 
+bool __read_mostly enable_device_posted_irqs = true;
+EXPORT_SYMBOL_GPL(enable_device_posted_irqs);
+
 const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
@@ -4990,6 +4993,8 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 	return kvm_arch_has_noncoherent_dma(vcpu->kvm);
 }
 
+static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu);
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -5012,6 +5017,19 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_x86_call(vcpu_load)(vcpu, cpu);
 
+	if (vcpu != per_cpu(last_vcpu, cpu)) {
+		/*
+		 * Flush the branch predictor when switching vCPUs on the same
+		 * physical CPU, as each vCPU needs its own branch prediction
+		 * domain.  No IBPB is needed when switching between L1 and L2
+		 * on the same vCPU unless IBRS is advertised to the vCPU; that
+		 * is handled on the nested VM-Exit path.
+		 */
+		if (static_branch_likely(&switch_vcpu_ibpb))
+			indirect_branch_prediction_barrier();
+		per_cpu(last_vcpu, cpu) = vcpu;
+	}
+
 	/* Save host pkru register if supported */
 	vcpu->arch.host_pkru = read_pkru();
 
@@ -7326,10 +7344,13 @@ set_pit2_out:
 		r = READ_ONCE(kvm->arch.default_tsc_khz);
 		goto out;
 	}
-	case KVM_MEMORY_ENCRYPT_OP: {
+	case KVM_MEMORY_ENCRYPT_OP:
+		r = -ENOTTY;
+		if (!kvm_x86_ops.mem_enc_ioctl)
+			goto out;
+
 		r = kvm_x86_call(mem_enc_ioctl)(kvm, argp);
 		break;
-	}
 	case KVM_MEMORY_ENCRYPT_REG_REGION: {
 		struct kvm_enc_region region;
 
@@ -8023,7 +8044,7 @@ static int emulator_read_write(struct x86_emulate_ctxt *ctxt,
 		return rc;
 
 	if (!vcpu->mmio_nr_fragments)
-		return rc;
+		return X86EMUL_CONTINUE;
 
 	gpa = vcpu->mmio_fragments[0].gpa;
 
@@ -9361,7 +9382,7 @@ static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pio.count = 0;
 
-	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip)))
+	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip)))
 		return 1;
 
 	return kvm_skip_emulated_instruction(vcpu);
@@ -9386,7 +9407,7 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
 			complete_fast_pio_out_port_0x7e;
 		kvm_skip_emulated_instruction(vcpu);
 	} else {
-		vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+		vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
 		vcpu->arch.complete_userspace_io = complete_fast_pio_out;
 	}
 	return 0;
@@ -9399,7 +9420,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
 	/* We should only ever be called with arch.pio.count equal to 1 */
 	BUG_ON(vcpu->arch.pio.count != 1);
 
-	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) {
+	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) {
 		vcpu->arch.pio.count = 0;
 		return 1;
 	}
@@ -9428,7 +9449,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
 		return ret;
 	}
 
-	vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+	vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
 	vcpu->arch.complete_userspace_io = complete_fast_pio_in;
 
 	return 0;
@@ -9811,6 +9832,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 	if (r != 0)
 		goto out_mmu_exit;
 
+	enable_device_posted_irqs &= enable_apicv &&
+				     irq_remapping_cap(IRQ_POSTING_CAP);
+
 	kvm_ops_update(ops);
 
 	for_each_online_cpu(cpu) {
@@ -10694,6 +10718,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 		return;
 
 	bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);
+	vcpu->arch.highest_stale_pending_ioapic_eoi = -1;
 
 	kvm_x86_call(sync_pir_to_irr)(vcpu);
 
@@ -12419,13 +12444,16 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	int idx;
+	int idx, cpu;
 
 	kvm_clear_async_pf_completion_queue(vcpu);
 	kvm_mmu_unload(vcpu);
 
 	kvmclock_reset(vcpu);
 
+	for_each_possible_cpu(cpu)
+		cmpxchg(per_cpu_ptr(&last_vcpu, cpu), vcpu, NULL);
+
 	kvm_x86_call(vcpu_free)(vcpu);
 
 	kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 88a9475899c8..832f0faf4779 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -121,6 +121,24 @@ static inline void kvm_leave_nested(struct kvm_vcpu *vcpu)
 	kvm_x86_ops.nested_ops->leave_nested(vcpu);
 }
 
+/*
+ * If IBRS is advertised to the vCPU, KVM must flush the indirect branch
+ * predictors when transitioning from L2 to L1, as L1 expects hardware (KVM in
+ * this case) to provide separate predictor modes.  Bare metal isolates the host
+ * from the guest, but doesn't isolate different guests from one another (in
+ * this case L1 and L2). The exception is if bare metal supports same mode IBRS,
+ * which offers protection within the same mode, and hence protects L1 from L2.
+ */
+static inline void kvm_nested_vmexit_handle_ibrs(struct kvm_vcpu *vcpu)
+{
+	if (cpu_feature_enabled(X86_FEATURE_AMD_IBRS_SAME_MODE))
+		return;
+
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+	    guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBRS))
+		indirect_branch_prediction_barrier();
+}
+
 static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.last_vmentry_cpu != -1;